© 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. 74051
    Prev
    Next
    INDEX
    Explanations

    location names and geographical references

    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
     str
    -0.07
    apo
    -0.07
     h
    -0.06
     g
    -0.06
    ureau
    -0.06
     ed
    -0.06
     Mus
    -0.06
    iversity
    -0.06
    burgh
    -0.06
    ix
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.09
    .Selenium
    0.08
    ırak
    0.08
    ίκ
    0.07
     Gould
    0.07
    onde
    0.07
     openFileDialog
    0.07
    'gc
    0.07
    .Container
    0.07
    StateManager
    0.07
    Activations Density 0.029%

    No Known Activations