© 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. 95660
    Prev
    Next
    INDEX
    Explanations

    key phrases and concepts related to health crises or outbreaks

    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
    à¥įवव
    -0.08
    zim
    -0.07
     straight
    -0.06
    ãģ¡ãģ¯
    -0.06
    /API
    -0.06
    .vs
    -0.06
    esium
    -0.06
    elters
    -0.06
    °}
    -0.06
    gpio
    -0.06
    POSITIVE LOGITS
    adel
    0.08
    /slick
    0.07
    alink
    0.07
    inder
    0.06
    iox
    0.06
    icient
    0.06
    ãĥ¼ãĤ¹ãĥĪ
    0.06
    æģĴ
    0.06
    iddle
    0.06
    ead
    0.06
    Activations Density 0.001%

    No Known Activations