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. 44133
    Prev
    Next
    INDEX
    Explanations

    references to cricket

    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
    اصÙĦÙĩ
    -0.07
     Tanner
    -0.07
    ANC
    -0.07
    /umd
    -0.06
    atoi
    -0.06
    utow
    -0.06
    å¹³æĪIJ
    -0.06
    ayne
    -0.06
     chain
    -0.06
    ات
    -0.06
    POSITIVE LOGITS
    icket
    0.15
    cket
    0.10
    кеÑĤ
    0.08
    lick
    0.08
    ctest
    0.08
    ICK
    0.08
    ic
    0.08
    ickets
    0.07
    icker
    0.07
     Cricket
    0.07
    Activations Density 0.003%

    No Known Activations