© 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. 15-LLAMASCOPE-RES-131K
    11. 61236
    Prev
    Next
    INDEX
    Explanations

    references to horse racing and betting outcomes

    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
    Å¡ti
    -0.07
    byn
    -0.07
    ectl
    -0.07
    asl
    -0.07
    bourne
    -0.06
    708
    -0.06
     NotImplemented
    -0.06
    inium
    -0.06
    charm
    -0.06
    ê±°ëŀĺê°Ģ
    -0.06
    POSITIVE LOGITS
     recent
    0.07
    innie
    0.06
    yo
    0.06
    Recent
    0.06
    recent
    0.06
     Advantage
    0.06
    expert
    0.06
     previous
    0.06
     Recent
    0.06
    imb
    0.06
    Activations Density 0.041%

    No Known Activations