© 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. 93982
    Prev
    Next
    INDEX
    Explanations

    references to organizations and networks involved in various contexts

    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
    etter
    -0.08
    ikon
    -0.07
    ptune
    -0.07
    icz
    -0.07
    787
    -0.06
     ÙħÙĨت
    -0.06
    reno
    -0.06
    iani
    -0.06
    anders
    -0.06
    th
    -0.06
    POSITIVE LOGITS
    ÙĨب
    0.06
    ió
    0.06
    375
    0.06
    ÂĢÂ
    0.06
     division
    0.06
    ÑĢÑĥд
    0.06
    AMI
    0.06
    ophage
    0.06
    ndata
    0.06
    ims
    0.06
    Activations Density 0.155%

    No Known Activations