© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3777
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stick" in various forms

    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
    ailles
    -0.07
    ana
    -0.06
    شت
    -0.06
    Âł
    -0.06
    for
    -0.06
    -0.06
     (
    -0.06
    fon
    -0.06
    oder
    -0.06
    irs
    -0.06
    POSITIVE LOGITS
     stick
    0.17
    Stick
    0.17
     Stick
    0.16
    stick
    0.15
     sticks
    0.14
     sticking
    0.14
    sticks
    0.13
     stuck
    0.10
    kees
    0.10
    ırak
    0.09
    Activations Density 0.003%

    No Known Activations