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

    Neuronpedia

    Jacobian LensNEW
    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. 75108
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes in various contexts

    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
    /or
    -0.09
    prop
    -0.08
    gi
    -0.07
    upt
    -0.07
    ingle
    -0.07
    eft
    -0.07
    eq
    -0.07
    -ÑĤо
    -0.07
    guard
    -0.07
    ses
    -0.07
    POSITIVE LOGITS
    zelf
    0.09
    wner
    0.07
    ideographic
    0.07
    avec
    0.07
    ksen
    0.07
    zano
    0.07
    ãĥ£
    0.07
    nice
    0.07
    nun
    0.07
    entimes
    0.07
    Activations Density 0.069%

    No Known Activations