© 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. 39599
    Prev
    Next
    INDEX
    Explanations

    elements related to dialogue, communication, and contextual interactions

    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
    feito
    -0.08
    ÃŃk
    -0.07
    owan
    -0.06
     Earl
    -0.06
    awi
    -0.06
    åŃĿ
    -0.06
    veau
    -0.06
    wal
    -0.06
    zb
    -0.06
     diá»ħn
    -0.06
    POSITIVE LOGITS
     Lau
    0.07
    agnostic
    0.07
    ipple
    0.06
    -resource
    0.06
     watchdog
    0.06
    ReadWrite
    0.06
    ToF
    0.06
    ivia
    0.06
    engu
    0.06
    оналÑĮ
    0.06
    Activations Density 0.388%

    No Known Activations