© 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. 18558
    Prev
    Next
    INDEX
    Explanations

    references to medical implants across various contexts

    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
    اÙĨÙĩ
    -0.07
    AMI
    -0.07
    istique
    -0.06
    lier
    -0.06
    KT
    -0.06
     æ©
    -0.06
    éĩı
    -0.06
     Tud
    -0.06
    vÃŃ
    -0.06
    aby
    -0.06
    POSITIVE LOGITS
    ation
    0.10
    able
    0.09
    ion
    0.08
    ations
    0.08
    zilla
    0.07
    ISMATCH
    0.07
    ions
    0.07
    owers
    0.07
    ive
    0.07
    zik
    0.07
    Activations Density 0.002%

    No Known Activations