© 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. 123273
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biometric systems

    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
    iku
    -0.07
    иÑĤоÑĢ
    -0.06
    cerr
    -0.06
     Incontri
    -0.06
    stag
    -0.06
    rch
    -0.06
    _pref
    -0.06
    ähr
    -0.06
     jaws
    -0.06
    edl
    -0.06
    POSITIVE LOGITS
     fingerprint
    0.07
    nist
    0.07
     human
    0.07
     criminal
    0.06
     uniqueness
    0.06
    human
    0.06
    inka
    0.06
     digit
    0.06
     digs
    0.06
     Human
    0.06
    Activations Density 0.008%

    No Known Activations