© 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. 41811
    Prev
    Next
    INDEX
    Explanations

    mentions of professional activities and organizational participation

    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
    é
    -0.06
    Ïĥμο
    -0.06
    ang
    -0.06
     yesterday
    -0.06
    .appspot
    -0.06
    iju
    -0.06
     onCancelled
    -0.06
    stalk
    -0.06
     compensated
    -0.06
    ONGL
    -0.06
    POSITIVE LOGITS
    inus
    0.08
    ottle
    0.07
    VICES
    0.07
    ãĤĽ
    0.07
    Annual
    0.07
     Annual
    0.07
    jist
    0.07
     annually
    0.07
    chten
    0.07
    oron
    0.06
    Activations Density 0.006%

    No Known Activations