© 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. 92036
    Prev
    Next
    INDEX
    Explanations

    references to actions of committing crimes or offenses

    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
    hints
    -0.07
    arry
    -0.07
    ÎŁÎ
    -0.07
    rray
    -0.07
    ayload
    -0.07
    ython
    -0.07
    zure
    -0.07
    stras
    -0.07
    ÑĨеп
    -0.07
    ¶Į
    -0.07
    POSITIVE LOGITS
     acts
    0.08
     feats
    0.07
    eson
    0.07
    tee
    0.07
     Hav
    0.06
     feat
    0.06
    acts
    0.06
     tasks
    0.06
    ocide
    0.06
    .NULL
    0.06
    Activations Density 0.007%

    No Known Activations