© 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. 15-LLAMASCOPE-RES-131K
    11. 87353
    Prev
    Next
    INDEX
    Explanations

    references to misinformation and its impact on public discourse

    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
     Hollande
    -0.07
    глÑı
    -0.07
    oÅĪ
    -0.07
    uess
    -0.07
    duino
    -0.07
    084
    -0.07
    684
    -0.07
    ÄĽle
    -0.06
    XMLElement
    -0.06
    inet
    -0.06
    POSITIVE LOGITS
    bs
    0.07
     кÑĥлÑĮ
    0.06
     Hutchinson
    0.06
     Dob
    0.06
     IG
    0.06
    ÑĢÑıд
    0.06
     trom
    0.06
     ants
    0.06
     loaders
    0.06
     Warp
    0.06
    Activations Density 0.093%

    No Known Activations