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. 43927
    Prev
    Next
    INDEX
    Explanations

    instances of achievements and recognition in a person's background

    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
    fte
    -0.06
    ondon
    -0.06
    756
    -0.06
    _specific
    -0.06
     Cush
    -0.06
    маг
    -0.06
     lesb
    -0.06
    TestCategory
    -0.06
    lice
    -0.06
    824
    -0.06
    POSITIVE LOGITS
     tab
    0.12
     named
    0.11
     voted
    0.10
     selected
    0.09
     part
    0.09
     tabs
    0.08
     invited
    0.08
     drafted
    0.08
     chosen
    0.08
     All
    0.08
    Activations Density 0.015%

    No Known Activations