© 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. 30941
    Prev
    Next
    INDEX
    Explanations

    references to shopping, particularly online shopping

    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
    utom
    -0.07
    uthor
    -0.07
    iones
    -0.07
    onders
    -0.06
    egers
    -0.06
    most
    -0.06
    ides
    -0.06
     Robbins
    -0.06
    ichten
    -0.06
    Äĥ
    -0.06
    POSITIVE LOGITS
    à¯įà®
    0.10
    tainment
    0.09
    lift
    0.08
    éĵº
    0.07
    /browse
    0.07
    몰
    0.07
    bone
    0.07
    lifting
    0.07
    rite
    0.07
     sprav
    0.07
    Activations Density 0.004%

    No Known Activations