© 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. 22-LLAMASCOPE-RES-131K
    11. 4162
    Prev
    Next
    INDEX
    Explanations

    terms related to health-related events and issues

    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
     statewide
    -0.07
     Gund
    -0.07
     Roe
    -0.07
     nationwide
    -0.06
    chner
    -0.06
    arra
    -0.06
    .ManyToMany
    -0.06
     madd
    -0.06
    kara
    -0.06
    538
    -0.06
    POSITIVE LOGITS
    (World
    0.11
    ettings
    0.08
    سÙĪ
    0.07
    leaflet
    0.07
     Laur
    0.07
    icom
    0.07
     Tunnel
    0.07
    iž
    0.07
    eya
    0.07
    iative
    0.07
    Activations Density 0.018%

    No Known Activations