© 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. 54182
    Prev
    Next
    INDEX
    Explanations

    references to swimming events and related environmental conditions

    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
     Moist
    -0.10
     humidity
    -0.10
     moisture
    -0.09
     damp
    -0.09
     moist
    -0.08
     humid
    -0.08
     Wet
    -0.08
    湿
    -0.07
     wet
    -0.07
    humidity
    -0.07
    POSITIVE LOGITS
    depth
    0.08
     swimming
    0.08
     Swim
    0.08
     depth
    0.08
     swim
    0.07
     shallow
    0.07
    886
    0.07
     Swimming
    0.07
    omanip
    0.07
    ìłĢ
    0.07
    Activations Density 0.108%

    No Known Activations