© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statistical outcomes or results

    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
    ighton
    -0.07
    orage
    -0.07
     Cyr
    -0.06
    chn
    -0.06
     Dorm
    -0.06
    yre
    -0.06
    gart
    -0.06
     Dust
    -0.06
    ario
    -0.06
     dust
    -0.06
    POSITIVE LOGITS
    antly
    0.09
    endir
    0.07
    atten
    0.07
    IDO
    0.07
    ADOS
    0.07
    Ïİ
    0.06
    astr
    0.06
    owing
    0.06
    urt
    0.06
    ancestor
    0.06
    Activations Density 0.021%

    No Known Activations