© 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. 106661
    Prev
    Next
    INDEX
    Explanations

    references to actions and their impacts

    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
    ÑģÑĤÑĢо
    -0.08
    stro
    -0.07
     ÑģÑĤановиÑĤÑĮ
    -0.07
    ideographic
    -0.07
    ToBounds
    -0.07
    .Surface
    -0.07
    siz
    -0.07
    istrovstvÃŃ
    -0.07
     thá»į
    -0.07
    statuses
    -0.07
    POSITIVE LOGITS
    /actions
    0.10
     actions
    0.10
    actions
    0.08
    inic
    0.08
    acts
    0.08
    -actions
    0.08
     towards
    0.07
     action
    0.07
     acts
    0.07
    -action
    0.07
    Activations Density 0.018%

    No Known Activations