© 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 EvalsExportsAPI 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. 57467
    Prev
    Next
    INDEX
    Explanations

    instances of the word "press" and its various forms, indicating a focus on pressure or pressing actions

    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
    atti
    -0.07
    nero
    -0.06
    -horizontal
    -0.06
    rol
    -0.06
    obi
    -0.06
    ActivityResult
    -0.06
    -pills
    -0.06
    /from
    -0.06
    olate
    -0.06
    maya
    -0.06
    POSITIVE LOGITS
     upon
    0.08
     onto
    0.07
     buttons
    0.07
    -button
    0.07
     harder
    0.06
     Button
    0.06
     button
    0.06
    button
    0.06
    nelly
    0.06
    buttons
    0.06
    Activations Density 0.009%

    No Known Activations