© 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. 96227
    Prev
    Next
    INDEX
    Explanations

    technical documentation related to engineering processes

    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
    åıİ
    -0.07
     Woodward
    -0.06
    ÏĨο
    -0.06
    leo
    -0.06
    rong
    -0.06
    ãģĭãĤĭ
    -0.06
    bral
    -0.06
    recover
    -0.06
    atrix
    -0.06
     Mara
    -0.06
    POSITIVE LOGITS
     design
    0.13
     Design
    0.12
    Design
    0.11
     DESIGN
    0.10
     drawings
    0.10
     designs
    0.10
    design
    0.10
     Designs
    0.09
    _design
    0.09
     Draw
    0.09
    Activations Density 0.086%

    No Known Activations