© 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. 17-LLAMASCOPE-RES-131K
    11. 79229
    Prev
    Next
    INDEX
    Explanations

    references to individuals or their personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éf
    -0.07
    elden
    -0.07
    ums
    -0.07
    ÄĽk
    -0.07
    avou
    -0.07
    avatars
    -0.07
    kees
    -0.07
    .xz
    -0.07
    maid
    -0.06
    CLUD
    -0.06
    POSITIVE LOGITS
     loved
    0.08
    ãĥ¼ãĥ«
    0.07
     Loved
    0.06
    145
    0.06
     pilgr
    0.06
     ir
    0.06
    åĭ¢
    0.06
    İ
    0.06
    #__
    0.06
    ä¸Ī
    0.06
    Activations Density 0.001%

    No Known Activations