© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104218
    Prev
    Next
    INDEX
    Explanations

    references to sexual violence and physical trauma

    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
    ë²Į
    -0.08
    berman
    -0.07
     Ãľl
    -0.07
    민
    -0.07
    ":""
    -0.07
    izzo
    -0.07
    olumn
    -0.07
    _DF
    -0.07
    ETCH
    -0.07
    Legend
    -0.07
    POSITIVE LOGITS
    us
    0.07
    h
    0.07
    w
    0.06
    lar
    0.06
    t
    0.06
    -avatar
    0.06
    iro
    0.05
    z
    0.05
    ous
    0.05
    F
    0.05
    Activations Density 0.053%

    No Known Activations