© 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. 98254
    Prev
    Next
    INDEX
    Explanations

    significant historical events or announcements

    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
    .wp
    -0.07
    pri
    -0.07
    pra
    -0.07
    #
    -0.07
    ducible
    -0.07
    ite
    -0.07
    batim
    -0.06
    ØŃب
    -0.06
    efully
    -0.06
    radu
    -0.06
    POSITIVE LOGITS
    ç¿
    0.06
    kud
    0.06
     Hao
    0.06
     McInt
    0.06
     Hawth
    0.06
    877
    0.06
    757
    0.06
    анÑĮ
    0.06
    ilen
    0.06
     Shel
    0.06
    Activations Density 0.029%

    No Known Activations