© 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. 123583
    Prev
    Next
    INDEX
    Explanations

    actions related to aggression or manipulation

    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
    anders
    -0.08
    elon
    -0.08
    eland
    -0.08
    .Companion
    -0.07
    okers
    -0.07
     Dün
    -0.07
    _FM
    -0.07
     osob
    -0.07
    erras
    -0.07
    esel
    -0.07
    POSITIVE LOGITS
    ingly
    0.09
     him
    0.08
     us
    0.08
    ibri
    0.07
    ishly
    0.07
     cred
    0.06
    ly
    0.06
     them
    0.06
     ach
    0.06
     directly
    0.06
    Activations Density 0.024%

    No Known Activations