© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89718
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to dimensions and borders

    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
    lich
    -0.07
    eniz
    -0.06
    ancel
    -0.06
    ekl
    -0.06
    oS
    -0.06
    Cipher
    -0.06
    dbl
    -0.06
    -side
    -0.06
    arda
    -0.06
     Zuk
    -0.06
    POSITIVE LOGITS
    aviest
    0.07
    /stdc
    0.07
    agle
    0.07
    ety
    0.07
    urious
    0.06
    liÄŁine
    0.06
    ιβ
    0.06
    venta
    0.06
    /tiny
    0.06
     Walton
    0.06
    Activations Density 0.003%

    No Known Activations