© 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. 123935
    Prev
    Next
    INDEX
    Explanations

    geographic names and institutional 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
     Chicago
    -0.08
     Dallas
    -0.08
     Texas
    -0.08
     Egypt
    -0.07
    Chicago
    -0.07
     Nigeria
    -0.07
     Egyptian
    -0.07
    Dallas
    -0.07
     Toronto
    -0.07
     chicago
    -0.07
    POSITIVE LOGITS
     Idaho
    0.13
     Boise
    0.12
     Nevada
    0.12
     Reno
    0.12
     Wyoming
    0.10
     NV
    0.10
     nev
    0.09
    NV
    0.09
     Nev
    0.09
    nev
    0.08
    Activations Density 0.155%

    No Known Activations