© 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. 69876
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and context within a document

    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
    510
    -0.07
    560
    -0.07
    erry
    -0.06
    512
    -0.06
    sv
    -0.06
    693
    -0.06
    935
    -0.06
    究
    -0.06
    210
    -0.06
    agi
    -0.06
    POSITIVE LOGITS
     duro
    0.07
    elay
    0.07
    ancer
    0.07
    iosa
    0.07
    ceptar
    0.07
    etro
    0.07
    дина
    0.07
    etri
    0.06
    terdam
    0.06
    amed
    0.06
    Activations Density 0.013%

    No Known Activations