© 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. 16036
    Prev
    Next
    INDEX
    Explanations

    mentions of pharmaceutical concepts and evidence of health-related subjects

    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
    ijd
    -0.08
    arrant
    -0.07
    taire
    -0.06
    ypse
    -0.06
    rowable
    -0.06
    vel
    -0.06
    archs
    -0.06
    IRTH
    -0.06
    ephir
    -0.06
    owitz
    -0.06
    POSITIVE LOGITS
    illy
    0.08
    oth
    0.08
     Ph
    0.07
     ph
    0.07
    rea
    0.07
    ysical
    0.07
    fy
    0.07
    gid
    0.07
    ishing
    0.07
    isco
    0.07
    Activations Density 0.024%

    No Known Activations