© 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. 92330
    Prev
    Next
    INDEX
    Explanations

    terms related to the NFL draft and its associated processes

    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
    iker
    -0.07
    oids
    -0.07
    acey
    -0.07
    ắp
    -0.06
    722
    -0.06
    ologna
    -0.06
    ocities
    -0.06
    bject
    -0.06
    ordin
    -0.06
     Solic
    -0.06
    POSITIVE LOGITS
    SKTOP
    0.08
    -day
    0.07
    able
    0.07
    RelativeTo
    0.07
    kea
    0.07
    tainment
    0.07
    orama
    0.07
    -wsj
    0.07
    apgolly
    0.07
    UrlParser
    0.07
    Activations Density 0.003%

    No Known Activations