© 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 EvalsExportsinterp-engineNEWAPI 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. 104359
    Prev
    Next
    INDEX
    Explanations

    descriptions of young adult characters and their personal journeys

    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
    imar
    -0.07
    éric
    -0.07
     SYS
    -0.07
    wyn
    -0.07
    ys
    -0.06
    lav
    -0.06
    .sys
    -0.06
    SYS
    -0.06
     Zig
    -0.06
    /il
    -0.06
    POSITIVE LOGITS
    esson
    0.07
    atro
    0.07
    muz
    0.06
    pector
    0.06
    asion
    0.06
    μÏĮ
    0.06
    omba
    0.06
    ollo
    0.06
    -prepend
    0.06
    singleton
    0.06
    Activations Density 0.084%

    No Known Activations