© 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. 1166
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, specifically codes or identifiers associated with technology or regulatory documents

    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
    are
    -0.07
    back
    -0.07
    दर
    -0.07
    finder
    -0.06
    usc
    -0.06
    mail
    -0.06
    ked
    -0.06
    xies
    -0.06
    andum
    -0.06
     èĩªåĬ¨çĶŁæĪIJ
    -0.06
    POSITIVE LOGITS
    eenth
    0.09
    een
    0.09
    als
    0.08
    esa
    0.07
    à¸ķà¸Ļ
    0.07
    ments
    0.07
    sse
    0.07
    nop
    0.07
    nÃŃ
    0.07
    lÃŃ
    0.07
    Activations Density 0.051%

    No Known Activations