© 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. 95257
    Prev
    Next
    INDEX
    Explanations

    discussions about rules and regulations, particularly those that are complex or confusing

    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
     Ãĸn
    -0.07
    æ·»
    -0.07
     whitelist
    -0.06
    arda
    -0.06
     shim
    -0.06
     tuyá»ĥn
    -0.06
    DataContract
    -0.06
     dna
    -0.06
    //{{
    -0.06
    StringValue
    -0.06
    POSITIVE LOGITS
     intest
    0.07
     rules
    0.07
    abis
    0.07
     law
    0.07
    ezi
    0.07
     complicated
    0.06
     legal
    0.06
    PLIC
    0.06
     Stat
    0.06
    -law
    0.06
    Activations Density 0.023%

    No Known Activations