© 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. 9-LLAMASCOPE-RES-131K
    11. 98948
    Prev
    Next
    INDEX
    Explanations

    terms related to counterfeit and piracy issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ë§Īëĭ¤
    -0.07
    aday
    -0.07
    ellow
    -0.06
    fell
    -0.06
    ampo
    -0.06
    ترÛĮ
    -0.06
    anian
    -0.06
    ductive
    -0.06
    unde
    -0.06
    kowski
    -0.06
    POSITIVE LOGITS
    áž
    0.07
    /cop
    0.07
    bdd
    0.06
    ci
    0.06
    ΣΤ
    0.06
    iveness
    0.06
    HDR
    0.06
    Ńå·ŀ
    0.06
     &'
    0.06
    ague
    0.06
    Activations Density 0.002%

    No Known Activations