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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5391
    Prev
    Next
    INDEX
    Explanations

    punctuation-related tokens, particularly quotes and colons

    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
    tract
    -0.06
     Weather
    -0.06
    fram
    -0.06
    aines
    -0.06
    TION
    -0.06
     Bars
    -0.06
     #__
    -0.06
     Peg
    -0.06
    hev
    -0.06
     utter
    -0.06
    POSITIVE LOGITS
    ouri
    0.07
    aterangepicker
    0.07
    oyer
    0.06
    pytest
    0.06
    oha
    0.06
    DonaldTrump
    0.06
    поÑģеÑĢед
    0.06
    afe
    0.06
    asher
    0.06
     unserialize
    0.06
    Activations Density 0.000%

    No Known Activations