© 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. 17-LLAMASCOPE-RES-131K
    11. 84892
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating power dynamics in social 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
    TION
    -0.08
     therefore
    -0.07
    sti
    -0.07
    atu
    -0.07
    iyon
    -0.06
     dann
    -0.06
    æĽ
    -0.06
    xed
    -0.06
    ús
    -0.06
    stre
    -0.06
    POSITIVE LOGITS
     there
    0.07
    isos
    0.07
    ugen
    0.07
    icos
    0.06
     most
    0.06
    avy
    0.06
    zeit
    0.06
    Æ°a
    0.06
    there
    0.06
    ppard
    0.06
    Activations Density 0.026%

    No Known Activations