Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106623
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fill" and related phrases, particularly in the context of completing forms or applications

    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
    meer
    -0.07
    iliz
    -0.06
    leasing
    -0.06
    лава
    -0.06
    wner
    -0.06
    벨
    -0.06
    prox
    -0.06
    ارا
    -0.06
    agen
    -0.06
    æĻĤ代
    -0.06
    POSITIVE LOGITS
     Wikispecies
    0.07
    abor
    0.07
    .fill
    0.07
    (fill
    0.07
    idel
    0.07
    »
    0.07
    ستر
    0.07
    otion
    0.06
    ikler
    0.06
     vals
    0.06
    Activations Density 0.003%

    No Known Activations