© 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. 82647
    Prev
    Next
    INDEX
    Explanations

    geographical data related to maps and counties

    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
    essler
    -0.06
    env
    -0.06
     Uni
    -0.06
     Caps
    -0.06
     æľĿ
    -0.06
     captive
    -0.06
    rita
    -0.06
     Americ
    -0.05
    Caps
    -0.05
    ream
    -0.05
    POSITIVE LOGITS
     mapa
    0.10
     UsersController
    0.08
    mapping
    0.08
     maps
    0.08
    455
    0.08
    ä¸ģ
    0.08
     mapping
    0.07
     map
    0.07
     ì¤
    0.07
    coverage
    0.07
    Activations Density 0.218%

    No Known Activations