© 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. 129917
    Prev
    Next
    INDEX
    Explanations

    HTML-related tags and formatting elements

    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
    OMEM
    -0.07
    \grid
    -0.07
    reesome
    -0.07
    eldon
    -0.07
    ::↵↵
    -0.07
    oco
    -0.07
    STYPE
    -0.07
    á»Ļn
    -0.07
    ISCO
    -0.07
    incare
    -0.07
    POSITIVE LOGITS
    ава
    0.06
    auer
    0.06
    andas
    0.06
    266
    0.06
    ëĤĺëĿ¼
    0.06
    cheme
    0.05
     Masc
    0.05
    elyn
    0.05
     unf
    0.05
    tbl
    0.05
    Activations Density 0.035%

    No Known Activations