© 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 EvalsExportsinterp-engineNEWAPI 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. 93328
    Prev
    Next
    INDEX
    Explanations

    structured formats and patterns in data representations

    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
     góc
    -0.07
    elpers
    -0.07
     تÙĦÙģ
    -0.07
    æ³Ĭ
    -0.07
    corner
    -0.07
    /helpers
    -0.07
    -corner
    -0.07
    å³°
    -0.07
    lags
    -0.07
    586
    -0.07
    POSITIVE LOGITS
     line
    0.16
     lines
    0.12
     Line
    0.12
    line
    0.12
    .line
    0.10
     Lines
    0.09
    -line
    0.09
    ç·ļ
    0.09
     LINE
    0.09
    Line
    0.09
    Activations Density 0.139%

    No Known Activations