© 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. 79313
    Prev
    Next
    INDEX
    Explanations

    remarks or comments that suggest sarcasm or criticism

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

    Transitional phrases, qualifiers, and evaluative language that signal the author's stance, frame relationships between ideas, or prepare the reader for interpretive content.

    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
    alsa
    -0.07
    esser
    -0.07
    -src
    -0.07
    actal
    -0.07
    å¡ļ
    -0.06
     Serialization
    -0.06
    ãĤĮãģ©
    -0.06
    lage
    -0.06
    å¸ĸ
    -0.06
     Pearce
    -0.06
    POSITIVE LOGITS
     reference
    0.20
     references
    0.17
    reference
    0.16
     Reference
    0.16
     refer
    0.15
    Reference
    0.15
     referring
    0.15
    /reference
    0.14
     referencia
    0.14
    .reference
    0.14
    Activations Density 0.076%

    No Known Activations