© 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. 107456
    Prev
    Next
    INDEX
    Explanations

    actions related to shopping and purchasing

    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
    imen
    -0.06
    amar
    -0.06
    phan
    -0.06
     MS
    -0.06
    igin
    -0.06
    ãĤ¤ãĥī
    -0.06
    ActionCreators
    -0.06
     Faul
    -0.06
    ãĥįãĥ«
    -0.06
     asset
    -0.06
    POSITIVE LOGITS
     essentials
    0.08
     supplies
    0.07
    lier
    0.07
    /stdc
    0.07
     bought
    0.07
     Bought
    0.07
     homo
    0.06
    ÏĢά
    0.06
    Ordered
    0.06
     INCIDENT
    0.06
    Activations Density 0.018%

    No Known Activations