© 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. 95230
    Prev
    Next
    INDEX
    Explanations

    patterns of numbers and references to events or statistics

    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
    warts
    -0.05
    -Cal
    -0.05
    Ñģи
    -0.05
    Illustr
    -0.05
    елÑİ
    -0.05
    ThemeProvider
    -0.05
    Ìģ
    -0.05
    NEXT
    -0.05
    غÙħ
    -0.05
    -In
    -0.05
    POSITIVE LOGITS
    otos
    0.08
    gv
    0.07
    анÑĤи
    0.07
     tol
    0.07
    luet
    0.07
    辺
    0.07
    ieten
    0.07
    ussen
    0.07
    amil
    0.06
    .XR
    0.06
    Activations Density 0.008%

    No Known Activations