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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78919
    Prev
    Next
    INDEX
    Explanations

    references to renewable energy and its impact on the environment

    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
     FAT
    -0.06
    ãĥ¼ãĥĩ
    -0.06
    elu
    -0.06
    HasKey
    -0.06
    eping
    -0.06
    ateway
    -0.06
     Brennan
    -0.06
    ãĤ¸ãĤª
    -0.06
     vap
    -0.06
    ahoo
    -0.06
    POSITIVE LOGITS
     power
    0.08
    ergy
    0.07
    power
    0.07
     Meg
    0.07
     feed
    0.07
     blade
    0.07
     Feed
    0.06
     carbon
    0.06
    ERGY
    0.06
     Blades
    0.06
    Activations Density 0.005%

    No Known Activations