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. 43843
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" and its variants in various contexts

    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
    /dialog
    -0.07
    ssel
    -0.07
     firstly
    -0.07
    æľĢåIJİ
    -0.07
    odesk
    -0.07
    -Identifier
    -0.07
    第ä¸Ģ次
    -0.06
     overposting
    -0.06
     cuá»iji
    -0.06
    uese
    -0.06
    POSITIVE LOGITS
    -ever
    0.21
    -time
    0.17
    born
    0.16
     few
    0.16
    s
    0.15
    -generation
    0.15
    -rate
    0.15
     ever
    0.15
    -hand
    0.14
    ever
    0.13
    Activations Density 0.108%

    No Known Activations