© 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. 130806
    Prev
    Next
    INDEX
    Explanations

    weather-related forecasts and probabilities

    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
     z
    -0.06
     imp
    -0.06
     Feinstein
    -0.05
    apse
    -0.05
     true
    -0.05
     Axe
    -0.05
     Lantern
    -0.05
     shoot
    -0.05
     Stam
    -0.05
     whose
    -0.05
    POSITIVE LOGITS
    ouser
    0.08
     kontakte
    0.07
    Ngh
    0.07
    ноÑģ
    0.07
    etag
    0.07
    ả
    0.07
     подаÑĤков
    0.07
    éĽ²
    0.07
    iji
    0.07
    μιÏĥ
    0.07
    Activations Density 0.006%

    No Known Activations