© 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. 95505
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries or collections

    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
    onders
    -0.07
    umed
    -0.07
    uÅŁ
    -0.07
    stag
    -0.06
     Patch
    -0.06
    etag
    -0.06
    ülük
    -0.06
    _descriptor
    -0.06
    usk
    -0.06
    tons
    -0.06
    POSITIVE LOGITS
    <fieldset
    0.07
    dorf
    0.06
    /lists
    0.06
    èİ
    0.06
    iero
    0.06
    /list
    0.06
    iculos
    0.06
    伯
    0.05
    .paging
    0.05
    rts
    0.05
    Activations Density 0.001%

    No Known Activations