© 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. 71583
    Prev
    Next
    INDEX
    Explanations

    references to underfunded or neglected health issues, particularly related to women's health and agriculture

    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
    丸
    -0.07
    ober
    -0.07
    ULO
    -0.07
    oxide
    -0.07
    irit
    -0.07
    elig
    -0.07
    eeper
    -0.07
     Prelude
    -0.06
    icas
    -0.06
    iffe
    -0.06
    POSITIVE LOGITS
     neglected
    0.15
     neglect
    0.15
     attention
    0.13
    ignored
    0.12
     ignored
    0.12
     Forgotten
    0.11
     Neg
    0.11
     forgotten
    0.11
    attention
    0.11
     overlooked
    0.11
    Activations Density 0.061%

    No Known Activations