© 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. 9-LLAMASCOPE-RES-131K
    11. 95691
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency response exercises and community events

    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
    loor
    -0.07
    ãģ¬
    -0.07
    pga
    -0.06
    ilha
    -0.06
    anchise
    -0.06
     tá»ĵn
    -0.06
    yped
    -0.06
    æ£ļ
    -0.06
     erv
    -0.06
     liqu
    -0.06
    POSITIVE LOGITS
    atel
    0.07
    ulfilled
    0.07
    ÅĻ
    0.06
    bur
    0.06
    berger
    0.06
    CLUDE
    0.06
    mar
    0.06
    -await
    0.06
    oogle
    0.06
    ding
    0.06
    Activations Density 0.036%

    No Known Activations