© 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. 85435
    Prev
    Next
    INDEX
    Explanations

    player names and associated actions 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
    inkel
    -0.08
    YLON
    -0.08
    ijo
    -0.08
    Âī
    -0.08
     ëĵ£
    -0.07
    êm
    -0.07
    SIDE
    -0.07
    PIX
    -0.07
    utos
    -0.07
    acades
    -0.07
    POSITIVE LOGITS
     Dare
    0.06
    æĽ¾
    0.06
     lead
    0.06
    Å¡k
    0.06
     leads
    0.05
     Bridges
    0.05
    .MixedReality
    0.05
     scores
    0.05
    kan
    0.05
     htt
    0.05
    Activations Density 0.018%

    No Known Activations