© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    infinitives or phrases indicating intention or movement

    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
    aran
    -0.08
    /goto
    -0.08
    stru
    -0.07
    .LookAndFeel
    -0.07
    -await
    -0.07
    ranÃŃ
    -0.07
    rieve
    -0.07
    /owl
    -0.07
    ismu
    -0.07
    aklı
    -0.07
    POSITIVE LOGITS
    /or
    0.09
    -to
    0.07
    /th
    0.06
     or
    0.06
    oled
    0.06
     o
    0.06
     upper
    0.06
    и
    0.06
     three
    0.06
    UInt
    0.06
    Activations Density 0.010%

    No Known Activations