© 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. 129685
    Prev
    Next
    INDEX
    Explanations

    mentions of medical recovery and treatments

    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
    rette
    -0.08
    STRING
    -0.07
    utch
    -0.07
    ÑĥÑĩа
    -0.06
    εÏį
    -0.06
    LocalizedString
    -0.06
    áŀ¶
    -0.06
     sink
    -0.06
    fas
    -0.06
     Goods
    -0.06
    POSITIVE LOGITS
     recovery
    0.09
     recovered
    0.09
     permanent
    0.08
     permanently
    0.07
     completely
    0.07
     normal
    0.07
     Recovery
    0.07
     recuper
    0.07
     normalization
    0.07
     fully
    0.07
    Activations Density 0.022%

    No Known Activations