© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1538
    Prev
    Next
    INDEX
    Explanations

    discussions around syncretism and its implications in religious or cultural contexts

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

    Academic discourse markers and evaluative phrases that structure arguments, qualify statements, or transition between ideas in scholarly or analytical writing.

    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
    -0.08
     (
    -0.07
    âĢ¦↵
    -0.07
    âĢ¦
    -0.07
    -
    -0.07
    il
    -0.07
     de
    -0.07
    .
    -0.06
    ,
    -0.06
    f
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.12
    .Reporting
    0.12
    ¯u
    0.11
    ÑĪиб
    0.10
    Äįel
    0.10
    .↵↵↵↵↵↵↵↵
    0.10
     Ñģигн
    0.10
    _QMARK
    0.10
    ìŀIJìĿ¸
    0.10
    chwitz
    0.10
    Activations Density 0.574%

    No Known Activations