© 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. 42667
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" within various contexts, particularly in programming or data structures

    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
    tero
    -0.07
    ior
    -0.06
    533
    -0.06
    Blend
    -0.06
    ará
    -0.06
     synd
    -0.06
    ROT
    -0.06
     Brad
    -0.06
    rouw
    -0.06
     Blend
    -0.06
    POSITIVE LOGITS
     enumerate
    0.09
    ายà¸Ļ
    0.07
    ophilia
    0.06
    oped
    0.06
    ensus
    0.06
    agg
    0.06
    à¹ĥ
    0.06
    åħ³ç³»
    0.06
     beaten
    0.06
    DMI
    0.06
    Activations Density 0.002%

    No Known Activations