© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42595
    Prev
    Next
    INDEX
    Explanations

    elements related to programming code and syntax

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     named
    -0.14
     Name
    -0.12
     name
    -0.12
     NAME
    -0.12
    named
    -0.11
     titled
    -0.11
    Name
    -0.10
     Named
    -0.10
    åIJįåŃĹ
    -0.10
    åIJį称
    -0.10
    POSITIVE LOGITS
     DESCRIPTION
    0.07
    :description
    0.07
    Ïĥί
    0.07
    	description
    0.07
    description
    0.06
    aru
    0.06
    hlen
    0.06
    (@(
    0.06
    arius
    0.06
     description
    0.06
    Activations Density 0.067%

    No Known Activations