© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77208
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes and styles in a CSS context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    eut
    -0.06
     Farr
    -0.06
    หว
    -0.06
     beg
    -0.06
    ENU
    -0.06
     Sez
    -0.06
     trimming
    -0.05
    _reporting
    -0.05
    strcasecmp
    -0.05
    rah
    -0.05
    POSITIVE LOGITS
    itori
    0.07
     Kis
    0.07
    feed
    0.06
    ัà¸Ĺ
    0.06
    lus
    0.06
    lain
    0.06
    iran
    0.06
     ãĢľ
    0.06
    pal
    0.06
    utra
    0.06
    Activations Density 0.003%

    No Known Activations