© 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. 89872
    Prev
    Next
    INDEX
    Explanations

    references to industrial plants and their various details

    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
    him
    -0.08
    eldon
    -0.08
    hip
    -0.07
    ê»ĺ
    -0.07
    uter
    -0.07
    edom
    -0.07
    ../../../
    -0.07
    anlı
    -0.07
    /name
    -0.07
    noop
    -0.07
    POSITIVE LOGITS
    lets
    0.09
    owner
    0.08
    ations
    0.08
    uar
    0.08
    igr
    0.08
    stead
    0.08
    igram
    0.08
    ings
    0.08
    owners
    0.08
    หà¸Ļ
    0.08
    Activations Density 0.018%

    No Known Activations