© 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. 62588
    Prev
    Next
    INDEX
    Explanations

    occurrences of comparative and descriptive statistics related to temperatures or weather 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
    uper
    -0.07
    ette
    -0.07
    iesel
    -0.07
    illow
    -0.07
     Cush
    -0.07
    affer
    -0.06
    andbox
    -0.06
    üb
    -0.06
    ignal
    -0.06
    UPER
    -0.06
    POSITIVE LOGITS
     bottoms
    0.07
    pa
    0.06
     ниж
    0.06
    ersen
    0.06
     bottom
    0.06
    lik
    0.06
     dew
    0.06
    Äij
    0.06
     Bottom
    0.06
     min
    0.06
    Activations Density 0.001%

    No Known Activations