© 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. 38207
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and correlations in data analysis

    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
    chop
    -0.08
    å¯
    -0.08
     Depths
    -0.07
    ÐĵÐŀ
    -0.07
    ìķĻ
    -0.06
     Kostenlose
    -0.06
    dorf
    -0.06
    Äįel
    -0.06
    ulum
    -0.06
    xin
    -0.06
    POSITIVE LOGITS
     lines
    0.08
     points
    0.08
     line
    0.08
     slope
    0.08
    points
    0.07
     curve
    0.07
     scatter
    0.07
    -points
    0.07
    -lines
    0.07
    adesh
    0.07
    Activations Density 0.189%

    No Known Activations