© 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. 105941
    Prev
    Next
    INDEX
    Explanations

    the frequency of different entities or groups in contexts related to sports or coaching

    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
    ucha
    -0.08
    706
    -0.07
     lesb
    -0.07
    .si
    -0.07
    ordinate
    -0.07
    LS
    -0.07
    irse
    -0.07
    anni
    -0.07
    STREAM
    -0.07
    онÑĮ
    -0.07
    POSITIVE LOGITS
     different
    0.16
    ä¸įåIJĮçļĦ
    0.14
    different
    0.13
     Different
    0.12
     khác
    0.11
    Different
    0.10
     diferentes
    0.10
    ifferent
    0.10
     farklı
    0.10
    ä¸įåIJĮ
    0.10
    Activations Density 0.027%

    No Known Activations