© 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. 27058
    Prev
    Next
    INDEX
    Explanations

    references to programming or technical specifications, particularly related to coding and effects processing

    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
    rink
    -0.08
     recording
    -0.07
     ÙĨÙĤØ´Ùĩ
    -0.07
    wy
    -0.07
     recordings
    -0.07
    Recording
    -0.07
    vox
    -0.07
    -fontawesome
    -0.07
    ouncer
    -0.06
     Recording
    -0.06
    POSITIVE LOGITS
     filter
    0.07
     filters
    0.07
    iment
    0.06
     Linked
    0.06
     sep
    0.06
    443
    0.06
    Dlg
    0.06
     HDR
    0.06
     values
    0.06
    åģı
    0.06
    Activations Density 0.007%

    No Known Activations