© 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. 5-LLAMASCOPE-RES-131K
    6. 125412
    Prev
    Next
    INDEX
    Explanations

    references to confusion or questioning specific situations

    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
    rais
    -0.07
    chn
    -0.06
    ijo
    -0.06
    utenberg
    -0.06
     somehow
    -0.06
    ask
    -0.05
    bilt
    -0.05
    ased
    -0.05
     advanced
    -0.05
     supplies
    -0.05
    POSITIVE LOGITS
    uffix
    0.08
    aÅĻ
    0.08
     oku
    0.07
    zego
    0.07
     iParam
    0.07
    ModelProperty
    0.07
    SGlobal
    0.07
    سÙĪØ¨
    0.07
    ohen
    0.07
    åIJIJ
    0.07
    Activations Density 0.003%

    No Known Activations