© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75307
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly apostrophes and periods

    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
    {'
    -0.10
    {}".
    -0.09
    ÑĮ
    -0.09
    ../../../
    -0.08
    {}",
    -0.08
    '''
    -0.08
    relude
    -0.08
    ’ta
    -0.07
    à¸Ĥà¸Ńà¸ĩà¸ľ
    -0.07
    gnore
    -0.07
    POSITIVE LOGITS
    ëį°
    0.09
    0.09
     “
    0.08
    ãģįãģŁ
    0.07
    .'↵
    0.07
    ñana
    0.07
    geh
    0.07
    .'↵↵
    0.07
    ž
    0.07
    '↵
    0.07
    Activations Density 0.272%

    No Known Activations