© 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. 60183
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific punctuation patterns or comma placements in contexts that suggest significant implications in narratives

    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
    ategy
    -0.07
    icensed
    -0.06
    .addObject
    -0.06
     ayrıca
    -0.06
     mouth
    -0.06
    atonin
    -0.06
    Ùģات
    -0.06
    ead
    -0.06
    atform
    -0.06
    deaux
    -0.06
    POSITIVE LOGITS
    _pagination
    0.07
     many
    0.07
     attention
    0.07
     questions
    0.06
    many
    0.06
    attention
    0.06
    riere
    0.06
     some
    0.06
     question
    0.06
    游
    0.06
    Activations Density 0.026%

    No Known Activations