© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95903
    Prev
    Next
    INDEX
    Explanations

    references to various types of medications and their effects

    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
    ава
    -0.07
    raph
    -0.06
    asar
    -0.06
    ewe
    -0.06
    vla
    -0.06
    thora
    -0.06
    757
    -0.06
    ÙĤÙĬØ©
    -0.06
    eced
    -0.06
     Rol
    -0.06
    POSITIVE LOGITS
    bote
    0.06
     hv
    0.06
     nackte
    0.06
    tie
    0.06
    parms
    0.06
    ãĥ¼ãĥĭ
    0.06
    .hl
    0.06
    çĩ
    0.06
    itech
    0.06
    (___
    0.06
    Activations Density 0.046%

    No Known Activations