© 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. 124377
    Prev
    Next
    INDEX
    Explanations

    references to historical status and designations of places or entities

    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
     Rosenberg
    -0.07
    andin
    -0.06
    alion
    -0.06
    kowski
    -0.06
    ollo
    -0.06
     دÙĪر
    -0.06
    cott
    -0.06
    ä¸ĢäºĽ
    -0.06
    aint
    -0.06
     Dün
    -0.06
    POSITIVE LOGITS
     Category
    0.06
    wi
    0.06
    wen
    0.06
    ủa
    0.06
     Special
    0.06
    eni
    0.06
    ady
    0.06
    utow
    0.06
    asil
    0.06
    aho
    0.06
    Activations Density 0.034%

    No Known Activations