© 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 EvalsExportsinterp-engineNEWAPI 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. 17603
    Prev
    Next
    INDEX
    Explanations

    references to spokespersons or spokesperson roles 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
    оже
    -0.07
    otel
    -0.07
    ütün
    -0.06
    chw
    -0.06
    335
    -0.06
    apus
    -0.06
    ologne
    -0.06
    à¸ļà¸Ĺ
    -0.06
    _ASSUME
    -0.06
     leader
    -0.06
    POSITIVE LOGITS
     spokesman
    0.14
     spokesperson
    0.13
     spokeswoman
    0.12
     communications
    0.12
     spokes
    0.10
     Communications
    0.10
     press
    0.10
    communications
    0.10
    Communic
    0.09
     communication
    0.09
    Activations Density 0.021%

    No Known Activations