© 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. 15-LLAMASCOPE-RES-131K
    11. 86219
    Prev
    Next
    INDEX
    Explanations

    terms related to frontline services or situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    åľ¨çº¿éĺħ读
    -0.09
    онÑĮ
    -0.09
    needle
    -0.08
    nten
    -0.08
    CLUDING
    -0.08
    thane
    -0.08
    ongan
    -0.08
    _planes
    -0.08
    oÄį
    -0.07
    ê´
    -0.07
    POSITIVE LOGITS
    iveau
    0.07
    /back
    0.07
    iers
    0.06
    olut
    0.06
     experience
    0.06
    /off
    0.06
     hous
    0.06
    /on
    0.05
     situations
    0.05
    /front
    0.05
    Activations Density 0.005%

    No Known Activations