© 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. 42058
    Prev
    Next
    INDEX
    Explanations

    references to kitchen utensils and cooking tools used in food preparation

    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
    hol
    -0.07
     Roose
    -0.07
    ence
    -0.07
    angu
    -0.07
    peak
    -0.07
    ãĥĽ
    -0.07
    agen
    -0.06
    ÑģÑĤиÑĤÑĥ
    -0.06
    ngo
    -0.06
     Vog
    -0.06
    POSITIVE LOGITS
     overnight
    0.06
     timelines
    0.06
    bras
    0.06
    izza
    0.06
     Kum
    0.06
     Exercise
    0.06
    sg
    0.05
     question
    0.05
     Overnight
    0.05
    ats
    0.05
    Activations Density 0.004%

    No Known Activations