© 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. 54798
    Prev
    Next
    INDEX
    Explanations

    specific time references and scheduling information

    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
    ural
    -0.07
     Holidays
    -0.06
    451
    -0.06
     springfox
    -0.06
     Ùĩد
    -0.06
    ÑģÑĤи
    -0.06
    ino
    -0.06
     Záp
    -0.06
     toh
    -0.06
    á»
    -0.06
    POSITIVE LOGITS
    igli
    0.07
    ilar
    0.06
    ignet
    0.06
    lij
    0.06
    ึà¸ģ
    0.06
     Teams
    0.06
    ugu
    0.06
     mitt
    0.06
    igure
    0.06
    riel
    0.06
    Activations Density 0.002%

    No Known Activations