© 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. 69194
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration or affection for people or ideas

    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
     expected
    -0.07
    reira
    -0.07
    ẩu
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    blade
    -0.07
    CAA
    -0.07
    çľ¾
    -0.06
    ê°ĢìļĶ
    -0.06
     Lois
    -0.06
    utsch
    -0.06
    POSITIVE LOGITS
    /lo
    0.08
    098
    0.07
    awns
    0.07
    /k
    0.06
    egen
    0.06
    oph
    0.06
     Slee
    0.06
     soph
    0.06
     Berm
    0.06
    ownt
    0.06
    Activations Density 0.026%

    No Known Activations