© 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. 86294
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "of course."

    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
    ospace
    -0.07
    avenport
    -0.06
    ustral
    -0.06
    IMARY
    -0.06
    /Typography
    -0.06
     thú
    -0.06
    alborg
    -0.06
    utin
    -0.06
    ượng
    -0.06
     Ridley
    -0.06
    POSITIVE LOGITS
    GetCurrent
    0.08
    istrovstvÃŃ
    0.08
    íĤ
    0.07
     maybe
    0.07
    bare
    0.06
    ziej
    0.06
    ä¹Łæľī
    0.06
    215
    0.06
     there
    0.06
    hdl
    0.06
    Activations Density 0.009%

    No Known Activations