© 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. 127827
    Prev
    Next
    INDEX
    Explanations

    references to leadership transitions and changes in executive roles within companies

    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
    lico
    -0.07
    inherit
    -0.07
    .override
    -0.06
    imeo
    -0.06
    otte
    -0.06
     repealed
    -0.06
    onald
    -0.06
    ÑĹв
    -0.06
     nich
    -0.06
    CASCADE
    -0.06
    POSITIVE LOGITS
    oux
    0.07
    fid
    0.07
    IRD
    0.07
     executive
    0.06
     early
    0.06
     Salary
    0.06
    lectic
    0.06
     Ñĥв
    0.06
    alary
    0.06
     EAR
    0.06
    Activations Density 0.010%

    No Known Activations