© 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. 70228
    Prev
    Next
    INDEX
    Explanations

    specific food ingredient mentions and cooking techniques

    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
     fkk
    -0.08
    CustomAttributes
    -0.08
    GuidId
    -0.07
    ÑģеÑĢ
    -0.07
    imbus
    -0.07
    uest
    -0.07
    lish
    -0.07
    END
    -0.07
    äch
    -0.07
     ydk
    -0.07
    POSITIVE LOGITS
     Broken
    0.06
    ategorized
    0.06
     deser
    0.06
    #c
    0.06
     nar
    0.06
     inj
    0.06
    Broken
    0.05
     ke
    0.05
     Agency
    0.05
     lul
    0.05
    Activations Density 0.002%

    No Known Activations