© 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. 108319
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics in a comparative context

    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
    635
    -0.06
     (
    -0.06
    itta
    -0.06
     blankets
    -0.05
    avl
    -0.05
     piger
    -0.05
    δι
    -0.05
    Contents
    -0.05
     silk
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
     sample
    0.14
     samples
    0.11
    -sample
    0.11
     SAMPLE
    0.11
     Sample
    0.11
    sample
    0.10
     datap
    0.10
    Sample
    0.10
     data
    0.10
     mẫu
    0.10
    Activations Density 0.072%

    No Known Activations