© 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. 98051
    Prev
    Next
    INDEX
    Explanations

    references to staircases and multi-story structures

    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
    ouro
    -0.09
    allel
    -0.07
    ç´ł
    -0.07
    avec
    -0.07
     Nest
    -0.07
    antity
    -0.07
    é»
    -0.07
    deen
    -0.07
    pies
    -0.07
    csr
    -0.07
    POSITIVE LOGITS
    оÑģÑĢед
    0.06
    bilt
    0.06
     keyed
    0.05
    lep
    0.05
     Bund
    0.05
    ños
    0.05
     ÏĦÏģÏĮ
    0.05
    .fromString
    0.05
    ëł¹
    0.05
     Mane
    0.05
    Activations Density 0.003%

    No Known Activations