© 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. 85351
    Prev
    Next
    INDEX
    Explanations

    instances of the word "don't" 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
    aybe
    -0.08
     schemes
    -0.07
    lider
    -0.07
    ÑĩаÑģ
    -0.07
    bage
    -0.07
    apiro
    -0.06
    stery
    -0.06
    cheme
    -0.06
    úa
    -0.06
    qt
    -0.06
    POSITIVE LOGITS
     worry
    0.07
    itz
    0.06
    /do
    0.06
     necessarily
    0.06
    angler
    0.06
     Carla
    0.06
     Barker
    0.06
    etz
    0.06
     Bureau
    0.06
    itr
    0.06
    Activations Density 0.015%

    No Known Activations