© 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 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. 126523
    Prev
    Next
    INDEX
    Explanations

    names and identifiers of key individuals in a sports context

    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
     guessed
    -0.06
    piring
    -0.06
    andalone
    -0.06
     Beck
    -0.06
    å¥ī
    -0.06
    erken
    -0.06
     verst
    -0.06
    NSMutable
    -0.06
    xca
    -0.06
    282
    -0.06
    POSITIVE LOGITS
     himself
    0.08
    /exec
    0.07
     decision
    0.07
    aset
    0.06
    asel
    0.06
     Decision
    0.06
    cker
    0.06
    lings
    0.06
    rial
    0.06
    oproject
    0.06
    Activations Density 0.041%

    No Known Activations