© 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. 40162
    Prev
    Next
    INDEX
    Explanations

    content related to climate change and environmental 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
     же
    -0.09
     trú
    -0.09
    à¹Ĩ
    -0.08
    /licenses
    -0.08
     à¹Ĩ
    -0.08
    ardy
    -0.08
    ãĢħ
    -0.08
    彡
    -0.08
    fest
    -0.08
    adesh
    -0.08
    POSITIVE LOGITS
    edly
    0.07
    -esque
    0.07
    bers
    0.07
    gers
    0.07
    phy
    0.06
    ckett
    0.06
    BoundingClientRect
    0.06
    -equipped
    0.06
    pers
    0.06
    (TM
    0.06
    Activations Density 2.354%

    No Known Activations