© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95845
    Prev
    Next
    INDEX
    Explanations

    references to application-type content and formats in programming contexts

    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
    iras
    -0.06
    peria
    -0.06
    aget
    -0.06
    æĭī
    -0.05
     Feedback
    -0.05
    ä¿
    -0.05
    olum
    -0.05
    perator
    -0.05
    section
    -0.05
    pare
    -0.05
    POSITIVE LOGITS
    adians
    0.07
    ánh
    0.07
     excer
    0.07
    ÃŃcia
    0.07
    è·
    0.07
    μαÏĦο
    0.07
    dados
    0.07
    ìĿ¸ìĿ´
    0.07
    IDL
    0.07
     Åŀu
    0.07
    Activations Density 0.001%

    No Known Activations