© 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. 86422
    Prev
    Next
    INDEX
    Explanations

    references to pages and pagination in documents

    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
    333
    -0.07
     patron
    -0.06
    _WRONG
    -0.05
     forg
    -0.05
    icket
    -0.05
    ig
    -0.05
    etta
    -0.05
     Biography
    -0.05
    etting
    -0.05
     undert
    -0.05
    POSITIVE LOGITS
    niÄį
    0.07
    ribbon
    0.07
    ürn
    0.07
    PRINTF
    0.07
    ibel
    0.07
     discrepan
    0.07
    inka
    0.07
    aspers
    0.07
    udem
    0.07
    apur
    0.07
    Activations Density 0.004%

    No Known Activations