© 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. 54523
    Prev
    Next
    INDEX
    Explanations

    instances of dates or numerical references in the text

    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
    ÄĽr
    -0.07
    DSA
    -0.06
    point
    -0.06
    idian
    -0.06
    etti
    -0.06
    ána
    -0.06
    817
    -0.06
    ालय
    -0.06
    áno
    -0.06
    iem
    -0.06
    POSITIVE LOGITS
    .son
    0.07
    vider
    0.07
    Ïĥα
    0.06
    (Have
    0.06
    Fcn
    0.06
    arov
    0.06
    Ñģклад
    0.06
    .enqueue
    0.06
    -caret
    0.06
    ìŀ¬
    0.06
    Activations Density 0.003%

    No Known Activations