© 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 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. 88710
    Prev
    Next
    INDEX
    Explanations

    references to power dynamics and negotiations in various contexts

    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
    azor
    -0.06
    ASC
    -0.06
    uess
    -0.06
    swire
    -0.06
    acerb
    -0.06
    itta
    -0.06
    ÑĢÑĥ
    -0.06
    iot
    -0.06
    wu
    -0.06
     deciding
    -0.06
    POSITIVE LOGITS
    æ³Ľ
    0.07
    chal
    0.06
     exped
    0.06
    licit
    0.06
    orex
    0.06
    hurst
    0.06
     íĿ¬
    0.06
    erek
    0.06
    shots
    0.06
    å´İ
    0.06
    Activations Density 0.024%

    No Known Activations