© 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. 88725
    Prev
    Next
    INDEX
    Explanations

    ellipses and other forms of punctuation related to pauses or omissions

    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
    itle
    -0.07
    uest
    -0.06
     pill
    -0.06
    ittest
    -0.06
    лем
    -0.06
    Ñīи
    -0.06
    ÑĢак
    -0.06
    Ñıд
    -0.06
    ropp
    -0.06
    ãģĹãģ¾
    -0.06
    POSITIVE LOGITS
    veis
    0.08
    -REAL
    0.08
    GetMethod
    0.07
    GetWidth
    0.07
    -FIRST
    0.07
    ¼åIJĪ
    0.07
     INCIDENTAL
    0.07
    .cljs
    0.07
    498
    0.07
    @nate
    0.06
    Activations Density 0.002%

    No Known Activations