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. 22-LLAMASCOPE-RES-131K
    6. 5647
    Prev
    Next
    INDEX
    Explanations

    mentions of nationalities and related cultural identifiers

    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
    äch
    -0.08
     franç
    -0.07
    gings
    -0.07
    chu
    -0.07
    PLEX
    -0.07
    thern
    -0.07
    -strokes
    -0.07
    adlo
    -0.07
    Ñī
    -0.07
    bidden
    -0.07
    POSITIVE LOGITS
    -American
    0.12
    -language
    0.12
    -speaking
    0.11
    -Russian
    0.10
    -Israel
    0.09
     national
    0.09
    ness
    0.09
    -made
    0.08
     Armed
    0.08
    ified
    0.08
    Activations Density 0.044%

    No Known Activations