© 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. 62808
    Prev
    Next
    INDEX
    Explanations

    instances of the word "find" and its derivatives

    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
    si
    -0.07
    FOUND
    -0.07
    BYTE
    -0.07
    found
    -0.06
    bsolute
    -0.06
    mage
    -0.06
    ìĨĮëħĦ
    -0.06
    -в
    -0.06
    ede
    -0.06
    ustum
    -0.06
    POSITIVE LOGITS
     out
    0.08
    imore
    0.07
    789
    0.07
    wal
    0.07
    ivo
    0.07
    iple
    0.07
     answers
    0.07
    imo
    0.06
    eneg
    0.06
    960
    0.06
    Activations Density 0.007%

    No Known Activations