© 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. 81098
    Prev
    Next
    INDEX
    Explanations

    a mix of special characters and specific formatting elements

    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
     PaÅŁa
    -0.07
    ekk
    -0.07
    onda
    -0.06
    htar
    -0.06
    lrt
    -0.06
     ØŃاÙĦت
    -0.06
    gin
    -0.06
    eyes
    -0.06
    oken
    -0.06
     adultes
    -0.06
    POSITIVE LOGITS
    kul
    0.07
    ansk
    0.06
    ANNEL
    0.06
    Łèĥ½
    0.06
    oulos
    0.06
     Burning
    0.06
    CJK
    0.06
     Bios
    0.06
    itemid
    0.06
    ichtet
    0.06
    Activations Density 0.003%

    No Known Activations