© 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. 89866
    Prev
    Next
    INDEX
    Explanations

    references to programming contexts or languages

    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
    VML
    -0.07
    جÙĩ
    -0.07
     ragaz
    -0.07
    inth
    -0.07
    ROTO
    -0.07
    θο
    -0.06
    ÎŃÏģα
    -0.06
    кол
    -0.06
    .CG
    -0.06
     Cage
    -0.06
    POSITIVE LOGITS
    éli
    0.07
    yat
    0.06
    emas
    0.06
    âķIJ
    0.06
    hod
    0.06
    anga
    0.06
    iesta
    0.06
    ÑĥÑĢа
    0.06
    acement
    0.06
    èle
    0.06
    Activations Density 0.015%

    No Known Activations