© 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. 57757
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "awkward" and related expressions

    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
    ätz
    -0.07
    paged
    -0.07
    czy
    -0.07
    สà¸Ķ
    -0.06
    Ñĥж
    -0.06
    .initialize
    -0.06
    ataka
    -0.06
    bildung
    -0.06
    enums
    -0.06
    keh
    -0.06
    POSITIVE LOGITS
    ness
    0.15
    ly
    0.11
    NESS
    0.10
     uncomfortable
    0.08
    nees
    0.08
    nes
    0.08
    -looking
    0.08
    edd
    0.08
    /conf
    0.08
    ities
    0.07
    Activations Density 0.005%

    No Known Activations