© 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. 17-LLAMASCOPE-RES-131K
    6. 39730
    Prev
    Next
    INDEX
    Explanations

    references to book recommendations and discussions about literature

    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
    .generated
    -0.06
    иÑģÑĮ
    -0.06
    vable
    -0.05
    arf
    -0.05
    είÏĦε
    -0.05
    sey
    -0.05
    _NC
    -0.05
    ovable
    -0.05
    EMA
    -0.05
    stery
    -0.05
    POSITIVE LOGITS
     book
    0.10
    recommended
    0.09
    book
    0.08
     кни
    0.08
    书
    0.08
     recommended
    0.08
     readable
    0.07
    /REC
    0.07
     recommendation
    0.07
    pdf
    0.07
    Activations Density 0.026%

    No Known Activations