© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-32K
    11. 32273
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names, including first and last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.25
    ey
    -0.17
    ing
    -0.16
    on
    -0.15
    æĿ¥æºIJ
    -0.14
    /down
    -0.14
     intermediate
    -0.14
    804
    -0.14
     comparative
    -0.14
     quadr
    -0.14
    POSITIVE LOGITS
    ibal
    0.19
    ála
    0.17
    oru
    0.16
    urat
    0.16
    enberg
    0.16
    sylvania
    0.16
    ìłIJ
    0.15
    sville
    0.15
    agi
    0.15
    vá
    0.15
    Activations Density 0.052%

    No Known Activations