© 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. 17-LLAMASCOPE-RES-131K
    11. 118746
    Prev
    Next
    INDEX
    Explanations

    specific congressional actions, sponsors, or legislative bills related to government proceedings

    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
     senator
    -0.11
     senators
    -0.11
     Senator
    -0.10
     senate
    -0.10
     Senators
    -0.10
    Senator
    -0.10
     SEN
    -0.10
    Sen
    -0.10
     Sen
    -0.09
     Senate
    -0.09
    POSITIVE LOGITS
     House
    0.10
     house
    0.09
     Speaker
    0.09
    House
    0.09
    .house
    0.08
     speaker
    0.08
    Speaker
    0.08
     HOUSE
    0.07
     Committee
    0.07
     Rep
    0.07
    Activations Density 0.188%

    No Known Activations