© 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. 15-LLAMASCOPE-RES-131K
    6. 27340
    Prev
    Next
    INDEX
    Explanations

    commercial and numerical data related to sales and performance metrics

    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
    .Apis
    -0.07
    innitus
    -0.07
    ibling
    -0.07
    upported
    -0.06
    ferred
    -0.06
    .YesNo
    -0.06
    WARDED
    -0.06
    kud
    -0.06
    adoras
    -0.06
     Ferry
    -0.06
    POSITIVE LOGITS
    à¸ļาà¸ĩ
    0.07
     actually
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
     Redistribution
    0.06
    à¥ĭà¤ļ
    0.06
     Flags
    0.06
    else
    0.06
    nuts
    0.06
     Howe
    0.06
    fce
    0.06
    Activations Density 0.008%

    No Known Activations