© 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. 9-LLAMASCOPE-RES-131K
    11. 99022
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and terms related to self-similar sets

    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
    ehler
    -0.07
    lobs
    -0.07
    igli
    -0.07
    ãĤĵãģ¨
    -0.07
     falling
    -0.07
     Falling
    -0.07
    abis
    -0.06
    bane
    -0.06
    ungan
    -0.06
    appen
    -0.06
    POSITIVE LOGITS
    yon
    0.07
    ÑģÑĤвÑĥ
    0.07
    ocking
    0.06
    orie
    0.06
     impression
    0.06
    zie
    0.06
    zc
    0.06
    DP
    0.06
    zier
    0.06
     stabil
    0.06
    Activations Density 0.010%

    No Known Activations