© 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. 96233
    Prev
    Next
    INDEX
    Explanations

    instances of people being arrested or involved in legal situations

    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
    бом
    -0.08
    ecut
    -0.07
    mb
    -0.07
     getUserId
    -0.07
    ãģĵãģ¨ãģ«
    -0.07
    funcs
    -0.07
    uele
    -0.06
     Pearce
    -0.06
    ÑĤÑĮ
    -0.06
    IEW
    -0.06
    POSITIVE LOGITS
     complaints
    0.07
     follow
    0.06
     allegedly
    0.06
    suma
    0.06
    rops
    0.06
     catch
    0.06
     concerned
    0.06
     o
    0.06
     investigation
    0.06
     reportedly
    0.06
    Activations Density 0.011%

    No Known Activations