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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43516
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes within a web form context

    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
    باش
    -0.06
    imon
    -0.06
    _MENU
    -0.06
    ãĥ«ãĥĪ
    -0.05
     Rounds
    -0.05
     Eld
    -0.05
     older
    -0.05
    vest
    -0.05
    schemas
    -0.05
    Inactive
    -0.05
    POSITIVE LOGITS
     radio
    0.11
    radio
    0.11
     controls
    0.11
    controls
    0.10
    -checkbox
    0.10
    _radio
    0.10
    checkbox
    0.10
    Controls
    0.10
     Radio
    0.10
     checkbox
    0.10
    Activations Density 0.011%

    No Known Activations