© 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. 9-LLAMASCOPE-RES-131K
    11. 94945
    Prev
    Next
    INDEX
    Explanations

    geographic locations and related cultural 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
    zy
    -0.06
    ono
    -0.06
    лÑĭ
    -0.06
     phys
    -0.06
     up
    -0.06
    zes
    -0.06
     nos
    -0.05
    ombo
    -0.05
     Econom
    -0.05
    .SDK
    -0.05
    POSITIVE LOGITS
    .synthetic
    0.08
    輪
    0.07
    AREN
    0.07
    esel
    0.07
    اش
    0.07
    mÃŃt
    0.07
    rust
    0.07
    omal
    0.07
    YPES
    0.07
    anken
    0.07
    Activations Density 0.009%

    No Known Activations