© 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. 18506
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and weaponry

    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
     actionTypes
    -0.06
     nut
    -0.06
    ble
    -0.06
     pneumonia
    -0.06
     uncomment
    -0.06
     steam
    -0.06
    874
    -0.06
    flag
    -0.05
     Nut
    -0.05
     Aud
    -0.05
    POSITIVE LOGITS
    Safety
    0.07
     recharge
    0.07
     pepper
    0.07
    翼
    0.07
    ucci
    0.07
     кÑĥÑģÑĤ
    0.07
     incapac
    0.07
     ÐĿаз
    0.07
     safety
    0.07
     Safety
    0.07
    Activations Density 0.001%

    No Known Activations