© 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. 125712
    Prev
    Next
    INDEX
    Explanations

    phrases related to vaccines and health information

    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
    Ñıг
    -0.08
    agma
    -0.07
    SSF
    -0.06
     Moderator
    -0.06
    Ì
    -0.06
     Kavanaugh
    -0.06
    [:,:,
    -0.06
    ³
    -0.06
    arez
    -0.06
    лод
    -0.06
    POSITIVE LOGITS
     measles
    0.09
     Hav
    0.06
    yms
    0.06
     coverage
    0.06
    Animation
    0.06
     animation
    0.06
    elden
    0.06
    DT
    0.06
    ukan
    0.06
     Animation
    0.06
    Activations Density 0.003%

    No Known Activations