© 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. 15-LLAMASCOPE-RES-131K
    11. 86619
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and individual perspectives

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

    Second-person address ("you" and related pronouns) that directly engages the reader, often in instructional or persuasive contexts.

    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
    .hh
    -0.07
    yx
    -0.07
    .scalablytyped
    -0.07
     ÎĶE
    -0.07
    Fit
    -0.07
    aub
    -0.06
    ÙĨس
    -0.06
     olab
    -0.06
    .metro
    -0.06
    ción
    -0.06
    POSITIVE LOGITS
     probably
    0.17
     likely
    0.15
    probably
    0.14
     Probably
    0.14
     possibly
    0.14
    Probably
    0.14
     maybe
    0.13
     perhaps
    0.13
    likely
    0.13
     Likely
    0.11
    Activations Density 0.056%

    No Known Activations