© 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. 123529
    Prev
    Next
    INDEX
    Explanations

    instructions related to navigating and utilizing web resources

    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
    елик
    -0.08
    ñana
    -0.08
     Progressive
    -0.07
    VERRIDE
    -0.07
    getApplication
    -0.07
    istrov
    -0.06
    ÙĬÙĥÙĬ
    -0.06
    enger
    -0.06
     progressive
    -0.06
    ãģĵãģ¨ãĤĤ
    -0.06
    POSITIVE LOGITS
    ahren
    0.07
    iž
    0.06
    BuilderFactory
    0.06
    CJK
    0.06
     thoroughly
    0.06
     cop
    0.06
    eni
    0.06
    WithURL
    0.06
    Terminal
    0.06
    noÅĽci
    0.06
    Activations Density 0.016%

    No Known Activations