© 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. 9-LLAMASCOPE-RES-131K
    11. 98624
    Prev
    Next
    INDEX
    Explanations

    phrases or references related to past events or actions

    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
     then
    -0.07
    lica
    -0.07
    inks
    -0.06
     Santos
    -0.06
    hire
    -0.06
     ↵↵
    -0.06
    then
    -0.06
    ied
    -0.05
    maz
    -0.05
    UIAlertView
    -0.05
    POSITIVE LOGITS
    /current
    0.07
    unce
    0.07
     IconData
    0.07
    affe
    0.07
    ograd
    0.07
    Runner
    0.07
    /original
    0.07
    awa
    0.06
    ãģĤãĤĭ
    0.06
    theless
    0.06
    Activations Density 0.010%

    No Known Activations