© 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. 103979
    Prev
    Next
    INDEX
    Explanations

    occurrences of the comma punctuation

    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
    arger
    -0.07
    opoulos
    -0.07
    wig
    -0.07
     dahil
    -0.07
    dad
    -0.07
    еб
    -0.07
    ãĥĭãĥĥãĤ¯
    -0.06
    arten
    -0.06
    ewis
    -0.06
    ogl
    -0.06
    POSITIVE LOGITS
     and
    0.09
    ãģĿãģĹãģ¦
    0.08
    and
    0.06
    ;
    0.06
    اکÙħ
    0.06
     Pur
    0.06
     же
    0.06
     vÃł
    0.06
     åĴĮ
    0.06
     Manhattan
    0.06
    Activations Density 0.017%

    No Known Activations