© 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. 108899
    Prev
    Next
    INDEX
    Explanations

    references to violence or combat-related terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    acher
    -0.07
    _bindings
    -0.07
    ctrine
    -0.07
    eyim
    -0.07
    emme
    -0.07
    ropoda
    -0.06
    ves
    -0.06
    sse
    -0.06
    anas
    -0.06
    ognition
    -0.06
    POSITIVE LOGITS
     powerful
    0.08
     discharge
    0.07
     strikes
    0.06
     моÑī
    0.06
     punches
    0.06
     laser
    0.06
    lander
    0.06
    direct
    0.06
     å¯
    0.06
     attack
    0.06
    Activations Density 0.094%

    No Known Activations