© 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. 22-LLAMASCOPE-RES-131K
    11. 4008
    Prev
    Next
    INDEX
    Explanations

    information related to treatment efficacy and outcomes for medical conditions

    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
     sebe
    -0.06
     Gib
    -0.06
     anomal
    -0.06
    von
    -0.05
     aff
    -0.05
     Boo
    -0.05
    hPa
    -0.05
     pav
    -0.05
     bearings
    -0.05
     bande
    -0.05
    POSITIVE LOGITS
     improvement
    0.11
     Improvement
    0.10
     achieved
    0.10
     improvements
    0.10
     responders
    0.09
     durable
    0.08
     achievement
    0.08
    plete
    0.08
     achieve
    0.08
    raphics
    0.07
    Activations Density 0.036%

    No Known Activations