© 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. 86297
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts and lawful procedures

    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
    enties
    -0.07
    urdu
    -0.07
    ulp
    -0.07
    çħ§
    -0.07
    ystone
    -0.07
    ftime
    -0.06
    essim
    -0.06
    rought
    -0.06
    yped
    -0.06
    _hr
    -0.06
    POSITIVE LOGITS
     imminent
    0.07
    iel
    0.07
     actively
    0.07
    antha
    0.06
     OMIT
    0.06
     neust
    0.06
     souÄįasné
    0.06
     cult
    0.06
    uchen
    0.06
    女åŃIJ
    0.05
    Activations Density 0.004%

    No Known Activations