© 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. 55420
    Prev
    Next
    INDEX
    Explanations

    words related to medical needs and interventions

    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
    á»
    -0.08
    lsi
    -0.07
    olik
    -0.07
     tắc
    -0.07
    à¹Ħว
    -0.07
    871
    -0.06
    allis
    -0.06
    vider
    -0.06
    дем
    -0.06
     Hayward
    -0.06
    POSITIVE LOGITS
     assistance
    0.08
    urr
    0.07
     intervention
    0.07
     help
    0.07
     special
    0.06
     treatment
    0.06
     specially
    0.06
     attention
    0.06
     further
    0.06
    asi
    0.06
    Activations Density 0.016%

    No Known Activations