© 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. 5-LLAMASCOPE-RES-131K
    11. 126396
    Prev
    Next
    INDEX
    Explanations

    terms associated with oxygen deficiency and related 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
    ÙĬج
    -0.07
    оваÑĢи
    -0.07
    tainment
    -0.07
    ente
    -0.06
    adle
    -0.06
    hof
    -0.06
    inic
    -0.06
    atten
    -0.06
    sg
    -0.06
     practition
    -0.06
    POSITIVE LOGITS
    LOCKS
    0.07
    rung
    0.07
    elerik
    0.07
     tip
    0.06
    .tip
    0.06
    otos
    0.06
    etry
    0.06
    å±±å¸Ĥ
    0.06
    conditions
    0.06
     Cyan
    0.06
    Activations Density 0.001%

    No Known Activations