© 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. 56297
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or institutions

    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
    iest
    -0.07
    ást
    -0.06
    antic
    -0.06
    ijo
    -0.06
    rf
    -0.06
    æĺİ
    -0.06
     mainstream
    -0.06
     either
    -0.05
    ubber
    -0.05
    ascade
    -0.05
    POSITIVE LOGITS
    purpose
    0.09
     purpose
    0.08
    'gc
    0.07
     mission
    0.07
    koli
    0.07
    дÑĸл
    0.07
    oldt
    0.07
     gangbang
    0.07
    orem
    0.07
    /effects
    0.07
    Activations Density 0.028%

    No Known Activations