© 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. 9-LLAMASCOPE-RES-131K
    11. 94112
    Prev
    Next
    INDEX
    Explanations

    terms related to data privacy and user rights

    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
     Tot
    -0.08
    pell
    -0.06
    lett
    -0.06
    ¢åįķ
    -0.06
    rawn
    -0.05
     pl
    -0.05
    aldi
    -0.05
    enberg
    -0.05
    ī
    -0.05
    åı£
    -0.05
    POSITIVE LOGITS
    ture
    0.07
    _mini
    0.07
    acle
    0.06
     dÃ¼ÅŁÃ¼r
    0.06
     Truy
    0.06
    Mini
    0.06
     ola
    0.06
    epar
    0.06
    ÑĤÑĢо
    0.06
    yat
    0.06
    Activations Density 0.001%

    No Known Activations