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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108425
    Prev
    Next
    INDEX
    Explanations

    dialogue and conversational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Markers that indicate or attribute dialogue, including quotation marks, speaker attribution verbs ("says", "replied"), and punctuation that follows or precedes direct speech.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    .djang
    -0.08
    eyh
    -0.07
    adele
    -0.07
    GuidId
    -0.07
    nte
    -0.07
    aign
    -0.07
    alar
    -0.07
    ogg
    -0.06
    orts
    -0.06
    intent
    -0.06
    POSITIVE LOGITS
     Answer
    0.08
     answer
    0.07
     question
    0.07
     answered
    0.06
     nothing
    0.06
    nothing
    0.06
     replied
    0.06
     Hudson
    0.06
     reply
    0.06
     answering
    0.06
    Activations Density 0.028%

    No Known Activations