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. 43449
    Prev
    Next
    INDEX
    Explanations

    specific structured data and attributes related to modules or formats in programming contexts

    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
     SpaceX
    -0.07
     yurt
    -0.07
    ergency
    -0.07
     Aerospace
    -0.06
     COVID
    -0.06
     Airbus
    -0.06
     unicorn
    -0.06
     Elon
    -0.06
     ‘
    -0.06
    ëĥ¥
    -0.06
    POSITIVE LOGITS
     Pink
    0.13
     mob
    0.12
     gang
    0.12
     Mafia
    0.11
     Mob
    0.11
     mafia
    0.11
    Pink
    0.11
     Sinatra
    0.10
     Gang
    0.10
    mob
    0.10
    Activations Density 0.003%

    No Known Activations