© 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. 40497
    Prev
    Next
    INDEX
    Explanations

    discussions about political candidates and their potential impact on elections

    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
    IRST
    -0.07
     Gallagher
    -0.07
    ï¸ı
    -0.06
     gist
    -0.06
    oster
    -0.06
    emoc
    -0.06
    assic
    -0.06
    761
    -0.06
    ritten
    -0.06
     DISPATCH
    -0.06
    POSITIVE LOGITS
     attempt
    0.07
     seper
    0.07
     attempts
    0.07
    ESSAGES
    0.06
    ials
    0.06
    burn
    0.06
    浪
    0.06
     attempting
    0.06
     SDS
    0.06
    !.↵↵
    0.06
    Activations Density 0.003%

    No Known Activations