© 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. 15-LLAMASCOPE-RES-131K
    11. 1401
    Prev
    Next
    INDEX
    Explanations

    references to specific drugs and their regulatory context

    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
     whe
    -0.07
    igham
    -0.07
    auses
    -0.06
    olla
    -0.06
    illas
    -0.06
    508
    -0.06
    ensen
    -0.06
    uilt
    -0.06
    uations
    -0.06
    conditionally
    -0.06
    POSITIVE LOGITS
    ãģķãĤī
    0.08
    ahan
    0.07
     chem
    0.07
    μÏĨ
    0.07
     dissoci
    0.07
     Safety
    0.07
     saf
    0.06
    -pos
    0.06
     synthetic
    0.06
    AMED
    0.06
    Activations Density 0.001%

    No Known Activations