© 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. 70031
    Prev
    Next
    INDEX
    Explanations

    references to specific cities or locations

    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
    éd
    -0.07
     craz
    -0.06
    éré
    -0.06
     Syndrome
    -0.06
     syndrome
    -0.06
    igmat
    -0.06
     paradox
    -0.06
     thr
    -0.06
     Speedway
    -0.06
    iday
    -0.05
    POSITIVE LOGITS
    bero
    0.08
    arrant
    0.07
     zda
    0.07
     GOODMAN
    0.07
    swire
    0.07
    units
    0.07
    HCI
    0.06
    帯
    0.06
    à¸Ķà¸Ļ
    0.06
    issen
    0.06
    Activations Density 0.000%

    No Known Activations