© 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. 121058
    Prev
    Next
    INDEX
    Explanations

    references to personal connections and shared 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
    anko
    -0.07
    CG
    -0.07
     Wor
    -0.07
    icamente
    -0.06
     mer
    -0.06
    emple
    -0.06
    etro
    -0.06
    akt
    -0.06
    vid
    -0.06
    erts
    -0.06
    POSITIVE LOGITS
    agu
    0.07
     majority
    0.07
    arer
    0.06
    ynom
    0.06
    _None
    0.06
    貨
    0.06
    èĥĮæĻ¯
    0.06
    .ContentType
    0.06
     çĻ¾
    0.06
    à¥ľ
    0.06
    Activations Density 0.033%

    No Known Activations