© 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 EvalsExportsAPI 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. 96810
    Prev
    Next
    INDEX
    Explanations

    reference to book titles and authors

    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
    letcher
    -0.07
    ecd
    -0.06
    _MAY
    -0.06
    urs
    -0.06
    efd
    -0.06
    bas
    -0.06
    icum
    -0.06
    ëĬIJ
    -0.06
    inkel
    -0.06
    inal
    -0.06
    POSITIVE LOGITS
     Companion
    0.06
    GLOBALS
    0.06
    ENCH
    0.06
     Chim
    0.06
    øj
    0.06
    endon
    0.06
    ibilidad
    0.06
     Darwin
    0.06
     assistir
    0.06
     brut
    0.06
    Activations Density 0.024%

    No Known Activations