© 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. 116363
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" in various contexts

    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
    chedulers
    -0.07
    berger
    -0.07
    AGR
    -0.06
    λλι
    -0.06
     Ãĸr
    -0.06
     ëIJĺìĹĪ
    -0.06
     Rehab
    -0.06
    enton
    -0.06
    -scalable
    -0.06
    ibri
    -0.06
    POSITIVE LOGITS
    hte
    0.07
    :
    0.07
    ï¸
    0.07
    ht
    0.06
    人人
    0.06
    qid
    0.06
     filt
    0.06
    veis
    0.06
    ocha
    0.06
    tes
    0.06
    Activations Density 0.002%

    No Known Activations