© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28131
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to climate change

    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
    Ïħκ
    -0.07
    ikel
    -0.07
    ãĤ¹ãĤ«
    -0.07
    andas
    -0.07
    slashes
    -0.07
     Dish
    -0.06
    aper
    -0.06
    деÑĢж
    -0.06
    opers
    -0.06
     INCIDENT
    -0.06
    POSITIVE LOGITS
    /weather
    0.10
    -change
    0.08
     change
    0.07
    /environment
    0.07
    agnostics
    0.07
    utton
    0.07
    $MESS
    0.07
    /tos
    0.07
    eka
    0.07
    /cl
    0.07
    Activations Density 0.009%

    No Known Activations