© 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. 120911
    Prev
    Next
    INDEX
    Explanations

    notable achievements and professional roles

    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
    akit
    -0.08
    imus
    -0.07
    weis
    -0.07
    atables
    -0.07
    agine
    -0.07
    į°
    -0.06
    icie
    -0.06
    erge
    -0.06
    .oper
    -0.06
    dna
    -0.06
    POSITIVE LOGITS
     ********************************************************************************
    0.07
     Laure
    0.06
    /extensions
    0.06
     st
    0.06
    308
    0.06
     gr
    0.06
     Cla
    0.06
    mast
    0.06
    575
    0.06
     retros
    0.06
    Activations Density 0.018%

    No Known Activations