© 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. 89735
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references related to specific events or postings

    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
    lund
    -0.08
     Hir
    -0.06
    vod
    -0.06
    ihn
    -0.06
     Latter
    -0.06
    etur
    -0.06
     zv
    -0.06
     working
    -0.06
     con
    -0.05
    ¤íĶĦ
    -0.05
    POSITIVE LOGITS
    æ³³
    0.07
    IXEL
    0.07
    OKIE
    0.07
    ByVersion
    0.06
    ocale
    0.06
    ROKE
    0.06
    undef
    0.06
    ongs
    0.06
    (reinterpret
    0.06
    ýt
    0.06
    Activations Density 0.009%

    No Known Activations