© 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. 77707
    Prev
    Next
    INDEX
    Explanations

    the use of the word "so" in various contexts

    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
    ká
    -0.07
    ritch
    -0.06
    eless
    -0.06
    oub
    -0.06
    GetCurrent
    -0.06
    ophon
    -0.06
    olley
    -0.06
    ledon
    -0.05
    lington
    -0.05
    asan
    -0.05
    POSITIVE LOGITS
     how
    0.14
     what
    0.12
    how
    0.11
     How
    0.10
    what
    0.10
    -how
    0.10
     Nasıl
    0.10
     why
    0.10
    How
    0.09
     cómo
    0.09
    Activations Density 0.006%

    No Known Activations