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

    Neuronpedia

    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. 107040
    Prev
    Next
    INDEX
    Explanations

    CSS styles and layout properties in web development

    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
    bolt
    -0.08
    amat
    -0.07
    viol
    -0.07
     Tá»īnh
    -0.07
    ноÑģÑĤ
    -0.06
     congr
    -0.06
    cmc
    -0.06
     strr
    -0.06
     scatter
    -0.06
    olit
    -0.06
    POSITIVE LOGITS
    ivals
    0.06
    lish
    0.06
    orte
    0.06
    éĸĵãģ«
    0.06
    _DIRS
    0.06
     Lynn
    0.06
    ovi
    0.06
    .li
    0.06
    VERTISEMENT
    0.06
    zyst
    0.06
    Activations Density 0.010%

    No Known Activations