© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1295
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms and court-related references

    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
    åĿĤ
    -0.07
    Drv
    -0.07
    egend
    -0.07
    %C
    -0.06
    adece
    -0.06
    ogany
    -0.06
    ahas
    -0.06
    owa
    -0.06
    etailed
    -0.06
    Detailed
    -0.06
    POSITIVE LOGITS
    /docs
    0.07
    setValue
    0.07
     court
    0.06
    ust
    0.06
    acket
    0.06
    ellen
    0.06
    EObject
    0.06
    323
    0.06
    èĢ³
    0.06
    rier
    0.06
    Activations Density 0.014%

    No Known Activations