© 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. 86486
    Prev
    Next
    INDEX
    Explanations

    specific mentions of health emergencies or events in public discussion

    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
    *)"
    -0.06
    ipeg
    -0.06
    ascus
    -0.06
    vester
    -0.06
    ewire
    -0.06
    cé
    -0.06
    176
    -0.06
     Capac
    -0.06
    stanov
    -0.06
    phies
    -0.06
    POSITIVE LOGITS
    ihan
    0.07
    UGC
    0.06
    à¤ģ
    0.06
    /pm
    0.06
    BlockSize
    0.06
    estion
    0.06
    Deferred
    0.06
    rame
    0.06
     Hancock
    0.06
    ãĥ©ãĥ³ãĥī
    0.06
    Activations Density 0.042%

    No Known Activations