© 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. 56974
    Prev
    Next
    INDEX
    Explanations

    lines or comments in code documentation

    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
    edar
    -0.07
    ousse
    -0.06
    \Bundle
    -0.06
    .xlsx
    -0.06
    en
    -0.06
     ãĤŃ
    -0.06
    вид
    -0.06
     jun
    -0.06
    stoup
    -0.06
    ÑĤон
    -0.06
    POSITIVE LOGITS
    endif
    0.07
    endregion
    0.07
     endregion
    0.07
    brick
    0.06
     endif
    0.06
    kova
    0.06
    FirstChild
    0.06
    ]]>
    0.06
    longleftrightarrow
    0.06
    AGIC
    0.06
    Activations Density 0.002%

    No Known Activations