© 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. 27533
    Prev
    Next
    INDEX
    Explanations

    various instances of individuals wearing specific types of clothing or disguise

    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
    olik
    -0.08
    roids
    -0.07
    autoload
    -0.07
    axed
    -0.07
    irie
    -0.07
    egra
    -0.07
    /REC
    -0.06
    raž
    -0.06
    ofilm
    -0.06
    woff
    -0.06
    POSITIVE LOGITS
     whites
    0.06
     nothing
    0.06
    cke
    0.06
    LV
    0.06
    ERY
    0.06
     hal
    0.06
    ivalence
    0.06
    hal
    0.06
     Redemption
    0.06
    ITHER
    0.05
    Activations Density 0.022%

    No Known Activations