© 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. 15-LLAMASCOPE-RES-131K
    11. 86997
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes and administrative responsibilities

    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
    ovah
    -0.07
    /loose
    -0.07
    frau
    -0.07
    orld
    -0.07
    kas
    -0.07
    ÙĪÛĮÙĦ
    -0.07
     iParam
    -0.07
    OffsetTable
    -0.07
    nÄĽm
    -0.07
     fav
    -0.07
    POSITIVE LOGITS
     local
    0.08
     locally
    0.07
     implementation
    0.07
     Local
    0.07
    local
    0.07
     themselves
    0.07
    Local
    0.06
     freely
    0.06
    -local
    0.06
     own
    0.06
    Activations Density 0.022%

    No Known Activations