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. 43451
    Prev
    Next
    INDEX
    Explanations

    elements related to travel and experiences

    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
     Bronx
    -0.06
     Wimbledon
    -0.06
     Harlem
    -0.06
    Britain
    -0.06
    linger
    -0.06
     Arlington
    -0.05
    áze
    -0.05
     Rutgers
    -0.05
     TEX
    -0.05
     ÑĢев
    -0.05
    POSITIVE LOGITS
     bus
    0.11
     buses
    0.10
     Bus
    0.09
    bus
    0.09
    /bus
    0.09
    Bus
    0.09
     hostel
    0.08
     Lonely
    0.08
     BUS
    0.08
     Uy
    0.08
    Activations Density 0.011%

    No Known Activations