© 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. 89448
    Prev
    Next
    INDEX
    Explanations

    metaphors and figurative language related to nature and transformation

    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
    aign
    -0.08
    áºŃu
    -0.07
     Nu
    -0.06
    azines
    -0.06
     appar
    -0.06
    variants
    -0.06
    ühr
    -0.06
    ifi
    -0.06
    iances
    -0.06
    zk
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥģ
    0.06
     FileMode
    0.06
    aille
    0.06
    owitz
    0.06
     Prelude
    0.06
     transformations
    0.06
    _Api
    0.06
     ê·¸ê²ĥ
    0.06
    (strategy
    0.06
     itself
    0.06
    Activations Density 0.009%

    No Known Activations