© 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. 116515
    Prev
    Next
    INDEX
    Explanations

    characters indicating the end of a function or block of code

    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
    eland
    -0.08
     Kop
    -0.07
    Obsolete
    -0.06
    ero
    -0.06
    uncate
    -0.06
    ÏĨα
    -0.06
    idade
    -0.06
     amp
    -0.05
     Fot
    -0.05
    843
    -0.05
    POSITIVE LOGITS
    itere
    0.07
    ãĥ³ãĤ¿
    0.07
    essler
    0.06
    alic
    0.06
    upert
    0.06
    VP
    0.06
    afari
    0.06
     ÎĶE
    0.06
    ittal
    0.06
    .running
    0.06
    Activations Density 0.020%

    No Known Activations