© 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. 1-LLAMASCOPE-RES-32K
    11. 19786
    Prev
    Next
    INDEX
    Explanations

    the word "still" in various contexts, indicating a focus on continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alyzed
    -0.16
    깨
    -0.15
    llib
    -0.14
    erce
    -0.14
    enal
    -0.14
    ãģķãģ¾
    -0.14
    ASA
    -0.14
    _INLINE
    -0.14
    asa
    -0.14
    equip
    -0.14
    POSITIVE LOGITS
    ness
    0.17
    tin
    0.16
    ÏĤ
    0.15
    s
    0.15
    jvu
    0.15
     intact
    0.14
    òn
    0.14
    spring
    0.14
    ensi
    0.14
    -fw
    0.14
    Activations Density 0.044%

    No Known Activations