© 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. 89834
    Prev
    Next
    INDEX
    Explanations

    the term "din" and its variations, indicating a focus on references to sound or noise

    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
    оÑģÑĮ
    -0.07
    Ú¯ÛĮ
    -0.07
    itaire
    -0.07
    LLL
    -0.06
     odst
    -0.06
     sin
    -0.06
    ständ
    -0.06
    Ñĥда
    -0.06
    markt
    -0.06
    e
    -0.06
    POSITIVE LOGITS
    osaurs
    0.08
    ostel
    0.07
    eldorf
    0.07
    amic
    0.07
    urnal
    0.07
    omite
    0.07
    ukkan
    0.06
    977
    0.06
    colo
    0.06
    zel
    0.06
    Activations Density 0.008%

    No Known Activations