© 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. 108712
    Prev
    Next
    INDEX
    Explanations

    words related to emission or emitting

    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
    irie
    -0.07
    rych
    -0.06
     boca
    -0.06
    ossal
    -0.06
    erox
    -0.06
    andal
    -0.06
    _RECE
    -0.06
     dÄ±ÅŁÄ±
    -0.06
    azio
    -0.06
    رز
    -0.06
    POSITIVE LOGITS
    大éĩı
    0.07
    /ion
    0.07
    folio
    0.06
    á»iji
    0.06
    åĿĤ
    0.06
    ikan
    0.06
     forth
    0.06
    ansson
    0.06
     signals
    0.06
    SSIP
    0.06
    Activations Density 0.023%

    No Known Activations