© 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. 108422
    Prev
    Next
    INDEX
    Explanations

    terms related to climate change and environmental action

    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
    roll
    -0.06
    laz
    -0.06
     jack
    -0.06
     McKenzie
    -0.06
    name
    -0.06
    turn
    -0.06
    nea
    -0.06
    ifle
    -0.06
    sville
    -0.05
    egl
    -0.05
    POSITIVE LOGITS
    -transitional
    0.07
    urope
    0.07
    esModule
    0.07
    ÑĤÑĢо
    0.07
    Å¡em
    0.07
    estro
    0.07
    asure
    0.07
    orarily
    0.07
    IDGET
    0.06
    plode
    0.06
    Activations Density 0.008%

    No Known Activations