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. 44179
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols commonly used in various scripts or languages

    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
     "
    -0.05
     Basket
    -0.05
     basket
    -0.05
    ļ
    -0.05
     '
    -0.05
    idas
    -0.05
     baskets
    -0.04
     Trotsky
    -0.04
    otron
    -0.04
    íĦ¸
    -0.04
    POSITIVE LOGITS
     perc
    0.13
     Perc
    0.12
    perc
    0.12
     soil
    0.10
     Soil
    0.10
     survey
    0.10
     drainage
    0.10
     sewer
    0.09
     homeowner
    0.09
    survey
    0.09
    Activations Density 0.003%

    No Known Activations