© 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. 5683
    Prev
    Next
    INDEX
    Explanations

    elements related to digital environments and technology

    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
    baugh
    -0.07
    ichick
    -0.06
    stery
    -0.05
    atta
    -0.05
    ónico
    -0.05
    terra
    -0.05
    abee
    -0.05
    angkan
    -0.05
     concurrently
    -0.05
    implify
    -0.05
    POSITIVE LOGITS
    unn
    0.08
    åı«
    0.08
    geh
    0.07
    Æł
    0.07
    _abstract
    0.07
    IRROR
    0.07
    uD
    0.07
    isel
    0.07
     nackt
    0.07
     ï¼į
    0.07
    Activations Density 0.068%

    No Known Activations