© 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. 60906
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions

    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
    rike
    -0.07
    atron
    -0.07
    親
    -0.07
    ãĢħ
    -0.07
     nues
    -0.07
    端
    -0.07
    omba
    -0.07
     slun
    -0.07
    าà¸ĩว
    -0.07
    iesta
    -0.07
    POSITIVE LOGITS
    .org
    0.09
    .ru
    0.07
    .net
    0.06
    byname
    0.06
    .biz
    0.06
    .com
    0.06
    0.06
    nbsp
    0.06
    oui
    0.06
    .blogspot
    0.06
    Activations Density 0.195%

    No Known Activations