© 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. 3575
    Prev
    Next
    INDEX
    Explanations

    instances of the word "been."

    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
    acie
    -0.08
    ocs
    -0.07
    _BUS
    -0.07
    boards
    -0.06
    ÏĢλ
    -0.06
    ems
    -0.06
    ãĥ¼ãĥį
    -0.06
    pies
    -0.06
    家ä¼Ļ
    -0.06
    isen
    -0.06
    POSITIVE LOGITS
    aller
    0.07
     able
    0.06
    ugi
    0.06
    toISOString
    0.06
    rouch
    0.06
    jamin
    0.06
    hta
    0.06
    @nate
    0.06
    rish
    0.06
    anic
    0.06
    Activations Density 0.010%

    No Known Activations