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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 94647
    Prev
    Next
    INDEX
    Explanations

    geographic locations and specific regions or landmarks

    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
     Coastal
    -0.09
    inu
    -0.09
     coastal
    -0.08
    ’Ñıз
    -0.07
     bay
    -0.07
     Neptune
    -0.07
    ĵĺ
    -0.07
    xee
    -0.07
    fang
    -0.07
    ilmington
    -0.07
    POSITIVE LOGITS
     Mountain
    0.11
     mountain
    0.10
    Mountain
    0.08
     mount
    0.08
     гÑĸÑĢ
    0.07
     Mountains
    0.07
     mountains
    0.07
     Mt
    0.07
    å±±
    0.07
     mining
    0.07
    Activations Density 0.132%

    No Known Activations