© 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. 107589
    Prev
    Next
    INDEX
    Explanations

    instances of physical violence or aggression

    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
    _IL
    -0.07
    Å¡lo
    -0.07
    اث
    -0.07
    stem
    -0.07
    acute
    -0.07
    posix
    -0.06
    quat
    -0.06
    155
    -0.06
     dumps
    -0.06
    اذ
    -0.06
    POSITIVE LOGITS
     anybody
    0.07
     anyone
    0.07
     somebody
    0.06
     âĹĦ
    0.06
     directly
    0.06
    ieren
    0.06
    iê
    0.06
    oque
    0.06
     him
    0.06
     everybody
    0.06
    Activations Density 0.023%

    No Known Activations