Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16470
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports events

    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
     Ferd
    -0.07
    ardless
    -0.07
     foreign
    -0.07
     Brass
    -0.06
     Ravens
    -0.06
    vailability
    -0.06
     Foreign
    -0.06
     chase
    -0.06
     Lowe
    -0.06
    Foreign
    -0.06
    POSITIVE LOGITS
    unan
    0.07
    elib
    0.07
    ans
    0.06
     ^{°}
    0.06
    onica
    0.06
    iping
    0.06
    ilst
    0.06
    illin
    0.06
    uff
    0.06
    usher
    0.06
    Activations Density 0.002%

    No Known Activations