© 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. 123251
    Prev
    Next
    INDEX
    Explanations

    services and products related to home repair and improvement

    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
    ãĥªãĥ¼ãĤº
    -0.07
    rve
    -0.07
    çĤ®
    -0.07
    ptom
    -0.07
    ernel
    -0.06
    ply
    -0.06
    Unicode
    -0.06
    itches
    -0.06
     Wings
    -0.06
    etto
    -0.06
    POSITIVE LOGITS
    jad
    0.08
     Crom
    0.06
    \-
    0.06
    _nb
    0.06
    amer
    0.06
    .cent
    0.06
    itori
    0.06
    ãĥ¼ãĥį
    0.06
    Highlighted
    0.06
    едÑĮ
    0.06
    Activations Density 0.018%

    No Known Activations