© 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. 40150
    Prev
    Next
    INDEX
    Explanations

    references to books and publications

    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
    ucas
    -0.07
    ige
    -0.06
    ẫn
    -0.06
    onn
    -0.06
    avir
    -0.06
    ushman
    -0.06
    atics
    -0.06
    _sdk
    -0.05
    611
    -0.05
    zeich
    -0.05
    POSITIVE LOGITS
     book
    0.08
    undles
    0.08
    /books
    0.08
    book
    0.08
    /book
    0.07
    iversit
    0.07
     books
    0.07
    title
    0.07
    elper
    0.07
    books
    0.07
    Activations Density 0.027%

    No Known Activations