© 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. 15-LLAMASCOPE-RES-131K
    11. 86416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" used in various contexts

    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
    ito
    -0.07
    tas
    -0.06
    suming
    -0.06
    alog
    -0.06
    vido
    -0.06
    lops
    -0.06
    iable
    -0.06
    348
    -0.06
    orsi
    -0.06
     Freeman
    -0.06
    POSITIVE LOGITS
    enser
    0.08
     why
    0.07
    adb
    0.07
    erner
    0.07
    uthor
    0.07
    herits
    0.07
    ikip
    0.06
    :
    0.06
    :↵
    0.06
    quires
    0.06
    Activations Density 0.010%

    No Known Activations