© 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 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. 82944
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental science and health

    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
    -based
    -0.08
    -Based
    -0.07
    -mediated
    -0.07
    stein
    -0.06
    лаж
    -0.06
    sik
    -0.06
    -led
    -0.06
    tures
    -0.06
     leading
    -0.06
    üh
    -0.06
    POSITIVE LOGITS
     potential
    0.09
    potential
    0.09
     Friendly
    0.08
    -support
    0.08
    Friendly
    0.08
     Potential
    0.08
    çĶ¨çļĦ
    0.07
     friendly
    0.07
     purposes
    0.07
    ìļ©
    0.07
    Activations Density 0.072%

    No Known Activations