© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 85042
    Prev
    Next
    INDEX
    Explanations

    content that discusses the size and influence of various groups and categories

    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
    eki
    -0.06
    OCI
    -0.06
    AMP
    -0.06
    rs
    -0.06
    (_)
    -0.06
    .appspot
    -0.06
    .rs
    -0.06
    pad
    -0.06
    apon
    -0.06
    ses
    -0.06
    POSITIVE LOGITS
    iddleware
    0.07
     sport
    0.07
    åº
    0.06
    ç£
    0.06
    pliant
    0.06
    itest
    0.06
    ÏģιÏĥ
    0.06
    sport
    0.06
    inar
    0.06
    anguages
    0.06
    Activations Density 0.034%

    No Known Activations