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. 22-LLAMASCOPE-RES-131K
    6. 5712
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes in a programming 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
    opsis
    -0.06
    umen
    -0.06
    mas
    -0.06
    awn
    -0.06
     Rock
    -0.06
    ample
    -0.06
    ileged
    -0.06
    177
    -0.06
     Kho
    -0.06
    ously
    -0.06
    POSITIVE LOGITS
    SRC
    0.09
     id
    0.08
     class
    0.08
     src
    0.08
    aria
    0.07
     SRC
    0.07
    class
    0.07
    CLASS
    0.07
     lang
    0.07
    urity
    0.07
    Activations Density 0.015%

    No Known Activations