© 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. 74353
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership or authority positions

    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
    arella
    -0.08
    steller
    -0.07
    Ń
    -0.07
    alysis
    -0.07
    ils
    -0.07
    éIJĺ
    -0.07
    ä¼
    -0.07
    ding
    -0.07
    rei
    -0.07
    sto
    -0.06
    POSITIVE LOGITS
    onet
    0.08
    ysize
    0.07
    erokee
    0.06
     at
    0.06
     thereof
    0.06
    luk
    0.06
    378
    0.06
     disp
    0.06
    antt
    0.06
     of
    0.06
    Activations Density 0.003%

    No Known Activations