© 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. 89868
    Prev
    Next
    INDEX
    Explanations

    references to legal charges and incidents involving individuals

    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
    ivent
    -0.07
    ÑĸнÑĮ
    -0.07
    atak
    -0.06
    lug
    -0.06
     Roma
    -0.06
     flush
    -0.06
    ¶Į
    -0.06
    å±ĭ
    -0.06
    æ¬Ĭ
    -0.06
    eger
    -0.06
    POSITIVE LOGITS
    070
    0.06
    é»
    0.06
     whilst
    0.06
    471
    0.06
    611
    0.06
    stay
    0.06
     '$
    0.06
     BPM
    0.06
    039
    0.06
     jac
    0.06
    Activations Density 0.001%

    No Known Activations