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. 11485
    Prev
    Next
    INDEX
    Explanations

    references to the country Paraguay

    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
     Kang
    -0.07
    èĢħ
    -0.06
     itemprop
    -0.06
     khá»ıe
    -0.06
    edException
    -0.06
    Sac
    -0.06
    .Lang
    -0.06
     Toro
    -0.06
     (!!
    -0.06
    asje
    -0.06
    POSITIVE LOGITS
    aguay
    0.21
    agu
    0.14
    ana
    0.12
    uguay
    0.12
    aug
    0.12
    aná
    0.11
    gu
    0.11
    ána
    0.11
    agua
    0.10
    ANA
    0.10
    Activations Density 0.003%

    No Known Activations