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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16267
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their context regarding geographical locations

    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
    elor
    -0.06
     ê²Įìĭľë¬¼
    -0.06
    ave
    -0.06
     Kiev
    -0.06
    hausen
    -0.05
     tuto
    -0.05
    qm
    -0.05
     bias
    -0.05
    uar
    -0.05
    unday
    -0.05
    POSITIVE LOGITS
     local
    0.13
     ours
    0.13
    local
    0.12
     locally
    0.12
     LOCAL
    0.11
    -local
    0.10
     localize
    0.10
     here
    0.10
    (local
    0.10
    LOCAL
    0.10
    Activations Density 0.337%

    No Known Activations