© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88042
    Prev
    Next
    INDEX
    Explanations

    instances of the word "imagine" and its variations

    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
    asthan
    -0.07
    unj
    -0.06
    tram
    -0.06
    cul
    -0.06
    ovna
    -0.06
    osto
    -0.06
    ses
    -0.06
    ients
    -0.06
    ocrates
    -0.06
    uded
    -0.06
    POSITIVE LOGITS
     yourself
    0.09
     imagine
    0.09
     Imagine
    0.08
    Imagine
    0.08
    etten
    0.07
    ably
    0.07
    ance
    0.07
    erd
    0.06
    777
    0.06
     scenario
    0.06
    Activations Density 0.005%

    No Known Activations