© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56452
    Prev
    Next
    INDEX
    Explanations

    places and locations that evoke community and connection

    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
     villages
    -0.07
    æĿij
    -0.07
     Village
    -0.07
     Overse
    -0.06
     Chicago
    -0.06
     Vill
    -0.06
     DISCLAIM
    -0.06
    ̧
    -0.06
    des
    -0.05
     Toronto
    -0.05
    POSITIVE LOGITS
     downtown
    0.17
     city
    0.14
     Downtown
    0.13
    owntown
    0.12
    -city
    0.11
     City
    0.11
    city
    0.10
    City
    0.10
     CITY
    0.10
    .city
    0.09
    Activations Density 0.228%

    No Known Activations