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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74418
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and measurements

    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
    ooter
    -0.07
    ucken
    -0.07
    å¥ı
    -0.06
     conf
    -0.06
    erview
    -0.06
     Morav
    -0.05
    ãĥ¡ãĥ©
    -0.05
    orean
    -0.05
     navig
    -0.05
     Sap
    -0.05
    POSITIVE LOGITS
    æĥ³åĪ°
    0.07
    ached
    0.07
     Thoughts
    0.07
    ómo
    0.07
    467
    0.07
    kazy
    0.07
    .='
    0.06
    impse
    0.06
    ÎłÎij
    0.06
    allo
    0.06
    Activations Density 0.002%

    No Known Activations