© 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. 26878
    Prev
    Next
    INDEX
    Explanations

    adjectives that convey positive qualities or attributes

    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
    shaw
    -0.07
    аÑĢаÑĤ
    -0.07
    akk
    -0.07
     suce
    -0.07
     tük
    -0.07
     reklam
    -0.07
    .om
    -0.07
    ìĿ´ëĤĺ
    -0.07
    idlo
    -0.07
    -mf
    -0.06
    POSITIVE LOGITS
     etc
    0.11
    çŃī
    0.08
    ãģĿãģĹãģ¦
    0.08
     ê·¸ë¦¬ê³ł
    0.07
    etc
    0.07
     ÑĤоÑīо
    0.06
    ãĤĪãģ³
    0.06
    940
    0.06
    memberof
    0.06
     approach
    0.06
    Activations Density 0.059%

    No Known Activations