© 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. 17528
    Prev
    Next
    INDEX
    Explanations

    components related to food and cooking experiences

    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
    isser
    -0.08
    ide
    -0.06
    lan
    -0.06
    agas
    -0.06
    yz
    -0.06
    ève
    -0.06
     These
    -0.06
    Ãħ
    -0.06
     Superior
    -0.06
     miss
    -0.06
    POSITIVE LOGITS
     whereas
    0.07
    ClientRect
    0.07
    Å¡ky
    0.07
    å¿į
    0.07
    ocity
    0.07
    ogn
    0.06
    alem
    0.06
    #ad
    0.06
    .cm
    0.06
     which
    0.06
    Activations Density 0.018%

    No Known Activations