© 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. 120689
    Prev
    Next
    INDEX
    Explanations

    geographical features and locations referenced in map-related contexts

    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
    erot
    -0.07
    arel
    -0.07
    ActionTypes
    -0.07
     Châu
    -0.07
     PLUS
    -0.07
    okud
    -0.07
    رÙĪج
    -0.07
    portun
    -0.07
    enet
    -0.06
    inel
    -0.06
    POSITIVE LOGITS
     summit
    0.07
     contour
    0.07
     contours
    0.06
     stream
    0.06
     benches
    0.06
     elev
    0.06
     benchmarks
    0.06
     crow
    0.06
     drainage
    0.06
     bench
    0.06
    Activations Density 0.104%

    No Known Activations