© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3820
    Prev
    Next
    INDEX
    Explanations

    terminology related to medical conditions 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
    azzi
    -0.07
    lyph
    -0.06
    ubble
    -0.06
     tavs
    -0.06
     Pact
    -0.06
    eryl
    -0.06
     Erg
    -0.06
     stake
    -0.06
    _STA
    -0.06
    inx
    -0.06
    POSITIVE LOGITS
    ariat
    0.09
     weight
    0.09
     Obesity
    0.08
     WEIGHT
    0.08
     obese
    0.08
     obesity
    0.07
     Weight
    0.07
     lept
    0.07
    Weight
    0.07
     gall
    0.07
    Activations Density 0.004%

    No Known Activations