© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4009
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue and conversational style in writing

    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
    aby
    -0.07
    onen
    -0.07
    azÄĥ
    -0.06
    é¬
    -0.06
     Ire
    -0.06
    ære
    -0.06
     Symbols
    -0.06
    olik
    -0.06
     tales
    -0.06
    links
    -0.06
    POSITIVE LOGITS
     dialogue
    0.20
     dialog
    0.17
     Dialogue
    0.16
    dialog
    0.16
    /dialog
    0.14
    -dialog
    0.14
    Dialogue
    0.14
    .dialog
    0.14
     speech
    0.13
     Dialog
    0.13
    Activations Density 0.035%

    No Known Activations