Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43745
    Prev
    Next
    INDEX
    Explanations

    data related to public opinion and polling results

    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
    ogie
    -0.07
    antt
    -0.07
    .Lang
    -0.07
    egot
    -0.07
     dign
    -0.07
    \Helpers
    -0.07
    åĬŁ
    -0.06
    bilder
    -0.06
    çľģ
    -0.06
    ÅĤu
    -0.06
    POSITIVE LOGITS
     support
    0.13
     attitudes
    0.12
     approval
    0.11
     respondents
    0.11
     views
    0.10
     Gallup
    0.10
     Americans
    0.10
     opinions
    0.10
     Support
    0.10
     poll
    0.10
    Activations Density 0.021%

    No Known Activations