© 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. 18584
    Prev
    Next
    INDEX
    Explanations

    expressions of observation or perception

    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
    ander
    -0.08
    orton
    -0.07
    smith
    -0.07
    vanished
    -0.07
    alte
    -0.07
    ÙĪتر
    -0.07
    ussen
    -0.07
    iem
    -0.07
     (("
    -0.07
    odore
    -0.07
    POSITIVE LOGITS
     us
    0.08
    rof
    0.07
     itself
    0.06
     a
    0.06
     brow
    0.06
     Ñģобой
    0.06
    353
    0.06
     introduction
    0.06
    blur
    0.06
     Prof
    0.06
    Activations Density 0.006%

    No Known Activations