© 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. 18842
    Prev
    Next
    INDEX
    Explanations

    components and features related to technology and organization

    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
    iola
    -0.09
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    lesai
    -0.07
    arde
    -0.07
    صة
    -0.07
    oji
    -0.07
    Dump
    -0.06
    ingen
    -0.06
    Trip
    -0.06
    inand
    -0.06
    POSITIVE LOGITS
     compat
    0.08
     compatible
    0.07
     or
    0.07
     compatibility
    0.07
     numerator
    0.07
     Äįi
    0.06
    æĪĸ
    0.06
     hoặc
    0.06
     eller
    0.06
     oder
    0.06
    Activations Density 0.025%

    No Known Activations