© 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. 62995
    Prev
    Next
    INDEX
    Explanations

    alphanumeric combinations, particularly identifying phone numbers or references to them

    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
    iper
    -0.08
    .nl
    -0.07
    uD
    -0.07
    rine
    -0.07
    utsch
    -0.07
    ož
    -0.07
    marker
    -0.06
    Resume
    -0.06
    WXYZ
    -0.06
    ansom
    -0.06
    POSITIVE LOGITS
    ιÏİ
    0.07
    ichtig
    0.06
     Pun
    0.06
     Ade
    0.06
    itere
    0.06
     Put
    0.06
    isons
    0.06
    ä¿
    0.06
    _GF
    0.06
     cou
    0.06
    Activations Density 0.001%

    No Known Activations