© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75322
    Prev
    Next
    INDEX
    Explanations

    references to specific players and their performance metrics in sports contexts

    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
    omon
    -0.07
    roupe
    -0.07
    _ASCII
    -0.06
    rete
    -0.06
    ilim
    -0.06
    pins
    -0.06
    pdata
    -0.06
     construct
    -0.06
    izoph
    -0.06
    /workspace
    -0.06
    POSITIVE LOGITS
     chief
    0.09
     lead
    0.08
     presidency
    0.07
     quarterback
    0.07
     Chief
    0.07
    etak
    0.07
     CEO
    0.07
     presidential
    0.07
     leadership
    0.07
    CEO
    0.07
    Activations Density 0.089%

    No Known Activations