© 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. 22-LLAMASCOPE-RES-131K
    11. 4311
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation indicating significant changes in context or updates

    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
    sted
    -0.06
    éĥİ
    -0.06
    elen
    -0.06
    æĹ¢
    -0.06
    bj
    -0.06
    une
    -0.06
    obo
    -0.06
    157
    -0.06
    pop
    -0.06
    ine
    -0.06
    POSITIVE LOGITS
    imde
    0.07
    ToDevice
    0.07
    ght
    0.07
    код
    0.07
    айд
    0.07
    adaÅŁ
    0.07
     åĽ
    0.07
    (EXPR
    0.06
    nem
    0.06
    sonian
    0.06
    Activations Density 0.000%

    No Known Activations