© 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. 57292
    Prev
    Next
    INDEX
    Explanations

    temperature measurements in various units

    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
     putas
    -0.09
    obao
    -0.08
     поба
    -0.07
     Ñĩин
    -0.07
    enci
    -0.07
    thur
    -0.07
    ruž
    -0.07
    ến
    -0.07
     desper
    -0.07
    .qq
    -0.07
    POSITIVE LOGITS
    hold
    0.06
    ux
    0.06
    ily
    0.06
     temperature
    0.06
    ym
    0.06
    ives
    0.06
     temperatures
    0.06
    -season
    0.06
    itt
    0.06
     Herrera
    0.06
    Activations Density 0.001%

    No Known Activations