© 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. 1291
    Prev
    Next
    INDEX
    Explanations

    instances of conflict and decision-making in tense 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
    ¯u
    -0.07
    immel
    -0.07
    .AnchorStyles
    -0.07
    Normalize
    -0.07
    ouz
    -0.06
    lanma
    -0.06
    اشÛĮ
    -0.06
    ProgressHUD
    -0.06
    _guid
    -0.06
    اÙħت
    -0.06
    POSITIVE LOGITS
     exit
    0.15
     fled
    0.14
     Exit
    0.14
    exit
    0.13
     departure
    0.13
     EXIT
    0.13
     flee
    0.13
    Exit
    0.13
     leaving
    0.13
     depart
    0.13
    Activations Density 0.107%

    No Known Activations