© 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. 75078
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing positive attributes and outcomes related to health and sustainability

    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
    reature
    -0.07
     novelty
    -0.06
    ساÙĨÛĮ
    -0.06
    ucked
    -0.05
    oded
    -0.05
    omens
    -0.05
     deps
    -0.05
    pak
    -0.05
     else
    -0.05
     opening
    -0.05
    POSITIVE LOGITS
    sense
    0.07
     balance
    0.07
     sense
    0.07
    à¥ĩष
    0.07
     Marvin
    0.07
    νοÏį
    0.06
    ç¦
    0.06
    eron
    0.06
     approach
    0.06
    stinence
    0.06
    Activations Density 0.046%

    No Known Activations