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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3161
    Prev
    Next
    INDEX
    Explanations

    references to sports events and participant details

    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
     Bilim
    -0.07
    ottes
    -0.07
    oreach
    -0.07
    iddleware
    -0.07
    pell
    -0.07
    AINER
    -0.07
    .Experimental
    -0.07
    ldb
    -0.07
    abox
    -0.07
    keley
    -0.06
    POSITIVE LOGITS
     represent
    0.07
     alongside
    0.07
     paternal
    0.07
     will
    0.07
     potentially
    0.07
     hoping
    0.06
    BUM
    0.06
    joining
    0.06
     represents
    0.06
     representing
    0.06
    Activations Density 0.018%

    No Known Activations