© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 14697
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Sheraton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the token "Sher" as part of proper nouns like "Sheraton," "Sherwood," "Sherbrooke," and names beginning with "Sher."

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    words or names beginning with the “Sher” prefix.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uae
    -0.15
    iesz
    -0.15
    ãĥ¥
    -0.15
    ej
    -0.15
    spo
    -0.14
    imir
    -0.14
    aal
    -0.14
    elli
    -0.13
    tep
    -0.13
    ãĥ¥ãĥ¼
    -0.13
    POSITIVE LOGITS
    iffs
    0.31
    aton
    0.24
     Sher
    0.23
    iff
    0.22
    lock
    0.22
    pherd
    0.21
     sher
    0.19
    rod
    0.18
    locks
    0.17
    idan
    0.17
    Activations Density 0.008%

    No Known Activations