© 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. 76539
    Prev
    Next
    INDEX
    Explanations

    references to prescription drugs and their dosages

    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
    Ìī
    -0.07
    rud
    -0.06
    annt
    -0.06
    gil
    -0.06
    immer
    -0.06
    enth
    -0.06
     fred
    -0.06
     Cald
    -0.06
    and
    -0.06
     abstraction
    -0.06
    POSITIVE LOGITS
    illion
    0.07
    eri
    0.06
     nasıl
    0.06
     how
    0.06
    berapa
    0.06
    éri
    0.06
    stav
    0.06
    /stdc
    0.06
     reviews
    0.06
    oston
    0.06
    Activations Density 0.001%

    No Known Activations