© 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. 108063
    Prev
    Next
    INDEX
    Explanations

    inquiries about costs or prices

    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
    оза
    -0.09
    онов
    -0.08
    εί
    -0.07
    voucher
    -0.07
    eyh
    -0.07
    Ñıб
    -0.07
    Portály
    -0.07
    vendors
    -0.07
    tero
    -0.07
    ungan
    -0.07
    POSITIVE LOGITS
     Gateway
    0.06
     Banc
    0.06
     taper
    0.05
     ZIP
    0.05
    yal
    0.05
    Gateway
    0.05
     ATM
    0.05
     tÃŃn
    0.05
    .StackTrace
    0.05
    iors
    0.05
    Activations Density 0.003%

    No Known Activations