© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29870
    Prev
    Next
    INDEX
    Explanations

    punctuation and its frequency usage in different contexts

    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
    esco
    -0.08
    ÑĸÑĶ
    -0.07
    ãģķãģĽ
    -0.07
    faf
    -0.07
     fisse
    -0.07
    _utilities
    -0.07
    ayment
    -0.07
    Kay
    -0.07
    oma
    -0.07
    âĢ¢↵↵
    -0.07
    POSITIVE LOGITS
    503
    0.07
    td
    0.06
     etc
    0.06
     ...)
    0.06
     Ov
    0.05
    The
    0.05
    466
    0.05
    913
    0.05
    504
    0.05
    EOF
    0.05
    Activations Density 0.005%

    No Known Activations