© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97546
    Prev
    Next
    INDEX
    Explanations

    conditions and situations related to compliance or adherence

    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
    rupa
    -0.07
    atÃŃm
    -0.07
    üzel
    -0.07
    ccione
    -0.07
    ãģĺãĤĥ
    -0.07
     exploitation
    -0.07
    igue
    -0.07
    &eacute
    -0.07
    utomation
    -0.07
    ih
    -0.07
    POSITIVE LOGITS
     or
    0.07
    373
    0.06
    477
    0.06
     elsewhere
    0.06
    /how
    0.06
    ocation
    0.06
    .Ver
    0.05
     Sunshine
    0.05
     voc
    0.05
    /models
    0.05
    Activations Density 0.020%

    No Known Activations