© 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. 91747
    Prev
    Next
    INDEX
    Explanations

    evaluations of products and their value for money

    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
    issen
    -0.07
    .boost
    -0.07
     empleado
    -0.07
    ì°Į
    -0.07
    \Php
    -0.07
    insi
    -0.07
     HAR
    -0.07
    å¹¹ç·ļ
    -0.07
    issy
    -0.07
    byter
    -0.07
    POSITIVE LOGITS
     bang
    0.13
     value
    0.10
     price
    0.09
    bang
    0.09
     cost
    0.09
     bargain
    0.08
     Value
    0.08
     VALUE
    0.08
    value
    0.08
     quality
    0.08
    Activations Density 0.065%

    No Known Activations