© 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. 30610
    Prev
    Next
    INDEX
    Explanations

    dates and time spans related to historical events or figures

    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
    achat
    -0.08
    sah
    -0.08
    rupa
    -0.07
    coil
    -0.07
    uyu
    -0.07
    leh
    -0.07
     eskort
    -0.07
    eydi
    -0.07
    ispens
    -0.07
    itou
    -0.07
    POSITIVE LOGITS
     Stam
    0.06
    ellen
    0.06
    AME
    0.06
     mand
    0.06
     Combined
    0.05
     syn
    0.05
     Mandal
    0.05
    ught
    0.05
    ogn
    0.05
    AD
    0.05
    Activations Density 0.008%

    No Known Activations