© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41947
    Prev
    Next
    INDEX
    Explanations

    elements related to navigation or structure in digital content

    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
    ucci
    -0.08
    ÐļТ
    -0.07
    epar
    -0.07
    áo
    -0.07
    ç«ľ
    -0.07
    ieux
    -0.07
    enci
    -0.07
    acket
    -0.07
    illez
    -0.07
    caffold
    -0.07
    POSITIVE LOGITS
    ếp
    0.06
    ometer
    0.06
    atas
    0.06
     Strength
    0.06
    won
    0.06
     disadv
    0.05
    ass
    0.05
    ouser
    0.05
     quick
    0.05
    Quick
    0.05
    Activations Density 0.003%

    No Known Activations