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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30020
    Prev
    Next
    INDEX
    Explanations

    references to locations, especially in the context of events or sports

    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
     Bristol
    -0.09
    ohl
    -0.08
     Mosul
    -0.08
     Iowa
    -0.08
    Liver
    -0.08
    ristol
    -0.07
     Liver
    -0.07
     Somerset
    -0.07
     tensorflow
    -0.07
    firebase
    -0.07
    POSITIVE LOGITS
     Dallas
    0.14
    Dallas
    0.13
     Chicago
    0.08
     Kazakhstan
    0.08
     Glasgow
    0.08
     Dubai
    0.07
    IBM
    0.07
     IBM
    0.07
    allas
    0.07
     Buenos
    0.07
    Activations Density 0.040%

    No Known Activations