© 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. 75019
    Prev
    Next
    INDEX
    Explanations

    programming-related function definitions and syntax

    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
    auga
    -0.07
    .java
    -0.06
     Chicago
    -0.06
    Chicago
    -0.06
     Grimm
    -0.06
    inois
    -0.06
    astle
    -0.06
    abus
    -0.06
    ModelProperty
    -0.06
    ึà¹Ī
    -0.06
    POSITIVE LOGITS
    Callbacks
    0.07
     liberated
    0.07
    apo
    0.07
    å¢
    0.06
     tinder
    0.06
     mall
    0.06
    Handlers
    0.06
     mort
    0.06
    adio
    0.06
     free
    0.06
    Activations Density 0.152%

    No Known Activations