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. 43820
    Prev
    Next
    INDEX
    Explanations

    concepts related to initiation ceremonies and their significance

    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
    ypi
    -0.07
    ubi
    -0.06
     Bundle
    -0.06
    lep
    -0.06
    umin
    -0.06
    aker
    -0.06
     Salman
    -0.06
    olean
    -0.06
    Pie
    -0.06
    AppBundle
    -0.06
    POSITIVE LOGITS
     Sr
    0.13
    ISK
    0.12
     vais
    0.12
    Sr
    0.11
     IS
    0.10
     devote
    0.10
     Cait
    0.10
     Krishna
    0.10
     Va
    0.09
     Åļ
    0.09
    Activations Density 0.041%

    No Known Activations