© 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. 17-LLAMASCOPE-RES-131K
    11. 127620
    Prev
    Next
    INDEX
    Explanations

    medical terms related to medications and their effectiveness

    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
    ilinear
    -0.06
    ourn
    -0.06
    qu
    -0.06
    51
    -0.05
    tright
    -0.05
     Globe
    -0.05
    ogo
    -0.05
     raw
    -0.05
    ancock
    -0.05
     unary
    -0.05
    POSITIVE LOGITS
    #ad
    0.09
    ReuseIdentifier
    0.08
    eltas
    0.08
    weg
    0.07
    .writ
    0.07
    bove
    0.07
    .writeString
    0.07
     tabi
    0.07
    _taken
    0.07
    _DF
    0.07
    Activations Density 0.006%

    No Known Activations