© 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. 30795
    Prev
    Next
    INDEX
    Explanations

    references to locations and geographic features

    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
     Carolina
    -0.08
     Connecticut
    -0.08
     Pennsylvania
    -0.08
     Bermuda
    -0.08
     Caribbean
    -0.07
     Illinois
    -0.07
     Florida
    -0.07
     Hurricanes
    -0.07
     hurricane
    -0.07
     Suffolk
    -0.07
    POSITIVE LOGITS
     Seattle
    0.26
    Seattle
    0.24
     Tacoma
    0.22
     Spokane
    0.20
     Vancouver
    0.18
     Seahawks
    0.17
     Oregon
    0.16
    okane
    0.16
     Pacific
    0.15
    Oregon
    0.15
    Activations Density 0.288%

    No Known Activations