© 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. 86590
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with medical or scientific data

    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
    ded
    -0.06
     ded
    -0.06
     chain
    -0.06
     inertia
    -0.06
     sober
    -0.06
    .Singleton
    -0.06
    UCE
    -0.06
    hal
    -0.05
     sinking
    -0.05
     Hal
    -0.05
    POSITIVE LOGITS
    orest
    0.08
    ixe
    0.07
    irim
    0.07
     sát
    0.07
    peech
    0.07
    Wunused
    0.07
    kening
    0.07
    ÑijÑĢ
    0.07
    Ñĥж
    0.07
    Ø·Ùĩ
    0.07
    Activations Density 0.005%

    No Known Activations