© 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. 73438
    Prev
    Next
    INDEX
    Explanations

    information regarding hotel locations and accessibility

    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
     McGregor
    -0.05
     tük
    -0.05
    βολ
    -0.05
     McKay
    -0.05
    ëĬ¥
    -0.05
    holm
    -0.05
     Dawson
    -0.05
     Large
    -0.05
     Sokol
    -0.05
     left
    -0.05
    POSITIVE LOGITS
     location
    0.19
    location
    0.16
     proximity
    0.16
     Location
    0.15
     LOCATION
    0.15
    Location
    0.15
    (location
    0.14
     ìľĦì¹ĺ
    0.14
     distance
    0.14
    è·Ŀ离
    0.14
    Activations Density 0.168%

    No Known Activations