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. 44335
    Prev
    Next
    INDEX
    Explanations

    demographic statistics related to race and population

    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
    ahun
    -0.07
    lias
    -0.07
    cket
    -0.07
    rand
    -0.06
    azu
    -0.06
    Ĩµ
    -0.06
    oop
    -0.06
    wil
    -0.06
    ój
    -0.06
    Defaults
    -0.06
    POSITIVE LOGITS
     Hispanic
    0.13
     Native
    0.12
     Asian
    0.12
     African
    0.11
     Latino
    0.11
     Race
    0.11
     race
    0.10
     White
    0.10
    Race
    0.10
     American
    0.10
    Activations Density 0.007%

    No Known Activations