© 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. 38447
    Prev
    Next
    INDEX
    Explanations

    occurrences of HTML or XML tags

    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
    ÑĥÑĪка
    -0.07
    isol
    -0.07
    esel
    -0.06
    æĸŃ
    -0.06
    xec
    -0.06
    enha
    -0.06
    ην
    -0.06
    ovation
    -0.06
    æĸ·
    -0.06
    ij
    -0.06
    POSITIVE LOGITS
    .Large
    0.07
    .vn
    0.07
     Kidd
    0.07
    виÑĤ
    0.07
    -signed
    0.07
    Raised
    0.06
    gor
    0.06
     barg
    0.06
    ืà¸Ńà¸ĩ
    0.06
    cdr
    0.06
    Activations Density 0.002%

    No Known Activations