© 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. 40630
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations and their surrounding areas

    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
    _NAMESPACE
    -0.08
     meis
    -0.07
    rend
    -0.07
    миÑĢ
    -0.06
    enez
    -0.06
    London
    -0.06
    andum
    -0.06
    alat
    -0.06
    egie
    -0.06
    atel
    -0.06
    POSITIVE LOGITS
     suburbs
    0.12
     suburban
    0.11
     countryside
    0.10
     rural
    0.09
     outer
    0.09
     outside
    0.09
     hinter
    0.08
    å¤ĸ
    0.08
     beyond
    0.08
     regional
    0.08
    Activations Density 0.044%

    No Known Activations