© 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. 9-LLAMASCOPE-RES-131K
    11. 98681
    Prev
    Next
    INDEX
    Explanations

    references to software and associated licensing terms

    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
    ibles
    -0.06
     company
    -0.06
    hin
    -0.06
    ner
    -0.05
    lyph
    -0.05
    itol
    -0.05
     among
    -0.05
     corpor
    -0.05
     TL
    -0.05
    ief
    -0.05
    POSITIVE LOGITS
    ENCH
    0.09
    ARRANT
    0.07
     lesb
    0.07
    iams
    0.07
    iddet
    0.07
    ãĤ¸ãĤ¢
    0.07
    odium
    0.07
    /MIT
    0.07
    _pulse
    0.07
    CRET
    0.07
    Activations Density 0.002%

    No Known Activations