© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125267
    Prev
    Next
    INDEX
    Explanations

    terms related to sports promotions and rankings

    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
    ugs
    -0.07
     Farr
    -0.06
    oons
    -0.06
     Sachs
    -0.06
     Apprec
    -0.06
    uth
    -0.06
     blat
    -0.06
    lob
    -0.06
     unw
    -0.06
    odka
    -0.06
    POSITIVE LOGITS
     into
    0.09
    into
    0.07
     from
    0.07
     via
    0.07
     khá»ıi
    0.07
     onto
    0.07
    iton
    0.07
    Into
    0.06
     revoked
    0.06
     industri
    0.06
    Activations Density 0.003%

    No Known Activations