© 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. 27808
    Prev
    Next
    INDEX
    Explanations

    references to ice and its properties in cold environments

    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
     damp
    -0.06
    emy
    -0.06
     TestCase
    -0.06
     Dil
    -0.06
     rainy
    -0.06
     wildfire
    -0.06
    lal
    -0.06
    norm
    -0.05
    oods
    -0.05
     нак
    -0.05
    POSITIVE LOGITS
     ice
    0.09
    ice
    0.08
     Ice
    0.07
     formations
    0.07
    _LAYER
    0.07
    Unsafe
    0.07
    thickness
    0.07
    icers
    0.07
    upy
    0.07
     thickness
    0.07
    Activations Density 0.014%

    No Known Activations