© 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 EvalsExportsAPI 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. 75044
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and names

    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
    ified
    -0.07
    plate
    -0.07
    ilities
    -0.07
    umber
    -0.07
    mÃŃ
    -0.06
     proh
    -0.06
    ifying
    -0.06
    ities
    -0.06
    ç±į
    -0.06
    ERRU
    -0.06
    POSITIVE LOGITS
    enance
    0.08
    yor
    0.07
    neck
    0.07
    ëıĦ
    0.07
    legg
    0.07
    lectric
    0.07
    çİĩ
    0.07
    ียà¸Ķ
    0.07
    çesi
    0.07
    ÛĮ
    0.07
    Activations Density 0.034%

    No Known Activations