© 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. 117909
    Prev
    Next
    INDEX
    Explanations

    mentions of prototype versions or testing phases

    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
     quarter
    -0.06
     e
    -0.06
    0
    -0.05
     __("
    -0.05
     Duke
    -0.05
     Challenger
    -0.05
    TRACT
    -0.05
     pomp
    -0.05
    ippers
    -0.05
    aph
    -0.05
    POSITIVE LOGITS
    InSection
    0.09
    awe
    0.08
    ynes
    0.08
     embr
    0.07
    URRED
    0.07
    Statics
    0.07
    ToWorld
    0.07
    outu
    0.07
     saldo
    0.07
     Heller
    0.07
    Activations Density 0.000%

    No Known Activations