© 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. 77091
    Prev
    Next
    INDEX
    Explanations

    references to parties and their involvement in legal or conflict scenarios

    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
    erli
    -0.08
    ski
    -0.07
    mie
    -0.07
    emek
    -0.07
    ERGE
    -0.07
    íĥĿ
    -0.07
    erie
    -0.07
    ondo
    -0.07
    arry
    -0.06
    ulan
    -0.06
    POSITIVE LOGITS
    /part
    0.09
    /all
    0.07
     involved
    0.07
    ways
    0.07
     parties
    0.07
    ing
    0.07
    icipants
    0.06
    hips
    0.06
    icipant
    0.06
    ä¹ĭä¸Ģ
    0.06
    Activations Density 0.007%

    No Known Activations