© 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. 18805
    Prev
    Next
    INDEX
    Explanations

    terms associated with corporate entities and organizational 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
     çĬ
    -0.06
    ,copy
    -0.06
    recht
    -0.06
    Xã
    -0.06
    å»
    -0.05
    achine
    -0.05
    ichel
    -0.05
    .habbo
    -0.05
    ÙİÙĥ
    -0.05
    ith
    -0.05
    POSITIVE LOGITS
    /Gate
    0.08
    errupt
    0.07
     nuest
    0.07
    .me
    0.07
    yonel
    0.07
    .ua
    0.06
     Roose
    0.06
    ftime
    0.06
    (){}↵↵
    0.06
    /GPL
    0.06
    Activations Density 0.005%

    No Known Activations