© 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. 86003
    Prev
    Next
    INDEX
    Explanations

    references to weather conditions and their impacts on travel

    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
    acid
    -0.08
    ammers
    -0.07
    .ci
    -0.07
    aims
    -0.07
    xdb
    -0.06
    ditor
    -0.06
    IPP
    -0.06
    aim
    -0.06
     Draws
    -0.06
    aises
    -0.06
    POSITIVE LOGITS
     snow
    0.17
     Snow
    0.15
    Snow
    0.14
    snow
    0.13
     snowy
    0.12
    éĽª
    0.11
     weather
    0.08
     ice
    0.08
     frozen
    0.08
     âĿ
    0.08
    Activations Density 0.052%

    No Known Activations