© 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. 30913
    Prev
    Next
    INDEX
    Explanations

    concepts related to organization and processes affected by external changes or conditions

    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
    if
    -0.06
    IF
    -0.06
    /
    -0.06
    w
    -0.06
    anger
    -0.06
    iw
    -0.06
    k
    -0.06
    ask
    -0.06
    er
    -0.06
    end
    -0.05
    POSITIVE LOGITS
    ÃŁen
    0.08
    LBL
    0.07
    odash
    0.07
    гал
    0.07
     EXEMPLARY
    0.07
    adir
    0.07
    .ta
    0.07
    alach
    0.07
     fetisch
    0.07
    Responder
    0.07
    Activations Density 0.002%

    No Known Activations