© 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. 81792
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to case evaluations

    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
    faction
    -0.09
    fak
    -0.07
    Advertisements
    -0.07
    ibern
    -0.07
     Careers
    -0.06
     careers
    -0.06
     TMPro
    -0.06
    erator
    -0.06
     programme
    -0.06
     tông
    -0.06
    POSITIVE LOGITS
    Ïĩη
    0.07
    clients
    0.06
    rete
    0.06
     office
    0.06
    auge
    0.06
     clients
    0.06
     Office
    0.06
    ogle
    0.06
     Offices
    0.06
     Egg
    0.06
    Activations Density 0.011%

    No Known Activations