© 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. 98588
    Prev
    Next
    INDEX
    Explanations

    cooking methods and ingredient preparations

    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
     Dem
    -0.06
    mour
    -0.06
    agnet
    -0.06
    onta
    -0.06
     –
    -0.06
    town
    -0.05
     -
    -0.05
     NAT
    -0.05
    oz
    -0.05
     Rice
    -0.05
    POSITIVE LOGITS
    unas
    0.08
    ÃĸL
    0.07
    utzer
    0.07
    ãĥ¼ãĥª
    0.07
    ãĥŃãĥ³
    0.07
    å®ı
    0.07
    AGR
    0.07
    iá»ĩt
    0.07
    lâm
    0.07
    ieten
    0.07
    Activations Density 0.083%

    No Known Activations