© 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. 95803
    Prev
    Next
    INDEX
    Explanations

    references to ratings, listings, and projects across various contexts

    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
     Feder
    -0.07
    ÑĪин
    -0.06
    557
    -0.06
    uyu
    -0.06
    olas
    -0.06
     com
    -0.06
    à¥įरश
    -0.06
    menin
    -0.06
    kap
    -0.06
    ulas
    -0.06
    POSITIVE LOGITS
    /apis
    0.07
    cha
    0.06
    à¹Ħà¸Ĥ
    0.06
     abide
    0.06
    bsd
    0.06
    adow
    0.06
    ersen
    0.06
    ouz
    0.06
    .Unicode
    0.06
    iper
    0.06
    Activations Density 0.018%

    No Known Activations