© 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. 30487
    Prev
    Next
    INDEX
    Explanations

    references to sports events and their results

    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
     versus
    -0.07
    lage
    -0.07
     vs
    -0.07
     junto
    -0.06
    bette
    -0.06
    oce
    -0.06
    ottes
    -0.06
    owie
    -0.06
    tero
    -0.06
    arshal
    -0.06
    POSITIVE LOGITS
     thereby
    0.06
    ascus
    0.06
    oola
    0.06
     Kut
    0.06
     tonight
    0.06
    utherford
    0.06
     hollow
    0.06
     aloud
    0.06
    کا
    0.06
     åŀ
    0.06
    Activations Density 0.021%

    No Known Activations