© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4007
    Prev
    Next
    INDEX
    Explanations

    instances of data or information related to specific events or statistics

    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
     Siz
    -0.07
     outr
    -0.07
    .ribbon
    -0.06
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    __,__
    -0.06
    Ù쨵ÙĦ
    -0.06
     详æĥħ
    -0.06
    ",__
    -0.06
     encodeURIComponent
    -0.06
    каÑģ
    -0.06
    POSITIVE LOGITS
     ten
    0.08
     five
    0.07
    usat
    0.06
     Ten
    0.06
     Thing
    0.06
    Ten
    0.06
    5
    0.06
    ix
    0.06
    GtkWidget
    0.06
    Thing
    0.05
    Activations Density 0.007%

    No Known Activations