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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118635
    Prev
    Next
    INDEX
    Explanations

    terminology related to serialization and data processing in programming

    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
    ordion
    -0.07
    iolet
    -0.06
    idders
    -0.06
    deer
    -0.06
    ipe
    -0.06
    ugen
    -0.06
    agged
    -0.06
    ibrary
    -0.06
    bag
    -0.06
    ibar
    -0.06
    POSITIVE LOGITS
    /json
    0.07
    altar
    0.06
    odal
    0.06
    oden
    0.06
    edla
    0.06
     пÑĢоб
    0.06
    anean
    0.06
     JSON
    0.06
    ISCO
    0.06
    asing
    0.06
    Activations Density 0.000%

    No Known Activations