© 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. 15-LLAMASCOPE-RES-131K
    11. 61762
    Prev
    Next
    INDEX
    Explanations

    terms related to diagnosis, particularly in medical contexts

    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
    ytut
    -0.07
    eview
    -0.07
    rito
    -0.07
    atoria
    -0.07
    thouse
    -0.07
     #__
    -0.07
    itori
    -0.07
    isors
    -0.07
    /accounts
    -0.07
    entina
    -0.06
    POSITIVE LOGITS
    etheless
    0.08
    adays
    0.08
    gether
    0.07
    west
    0.07
    atre
    0.07
    noc
    0.07
    thinkable
    0.06
    /-
    0.06
    ï¸
    0.06
    yer
    0.06
    Activations Density 0.102%

    No Known Activations