© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    commands related to including figures and graphics in a document

    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
     赤
    -0.07
    etu
    -0.07
    erta
    -0.07
    lte
    -0.06
    arel
    -0.06
    hatt
    -0.06
    iets
    -0.06
    zá
    -0.06
    remen
    -0.06
    WT
    -0.06
    POSITIVE LOGITS
    offsetof
    0.06
    valueOf
    0.06
    sizeof
    0.06
     Gross
    0.06
     indirect
    0.06
     assistir
    0.06
    tbl
    0.06
    rowse
    0.05
    cipher
    0.05
    icable
    0.05
    Activations Density 0.010%

    No Known Activations