© 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. 15-LLAMASCOPE-RES-131K
    11. 61531
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" and variations in its usage throughout the text

    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
    rant
    -0.07
    vala
    -0.06
    in
    -0.06
    ovy
    -0.06
    orny
    -0.06
    acock
    -0.06
     Clair
    -0.06
    liament
    -0.06
    kol
    -0.05
    ccoli
    -0.05
    POSITIVE LOGITS
    BBBB
    0.07
    deniz
    0.07
    WSC
    0.07
    اÙĪÙĬ
    0.06
    amespace
    0.06
    enco
    0.06
    ãģĸ
    0.06
    IRT
    0.06
    anel
    0.06
    veis
    0.06
    Activations Density 0.002%

    No Known Activations