© 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. 17567
    Prev
    Next
    INDEX
    Explanations

    descriptions related to uncertainty in environmental data, particularly concerning temperature

    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
    amble
    -0.07
    _HDR
    -0.07
    icho
    -0.07
    atel
    -0.06
    allax
    -0.06
    ptest
    -0.06
    occo
    -0.06
    èŃ
    -0.06
    rought
    -0.06
     CircularProgress
    -0.06
    POSITIVE LOGITS
     green
    0.13
     color
    0.11
     blue
    0.11
    green
    0.11
     yellow
    0.11
     red
    0.10
     orange
    0.10
    绿
    0.09
     colour
    0.09
    blue
    0.09
    Activations Density 0.053%

    No Known Activations