© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29908
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Fat" and its variations

    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
    tte
    -0.07
    hower
    -0.07
    pton
    -0.07
    atör
    -0.07
    atrix
    -0.07
    tape
    -0.07
    stal
    -0.07
    tank
    -0.07
    ades
    -0.07
    orative
    -0.06
    POSITIVE LOGITS
    igue
    0.10
    ened
    0.09
    ima
    0.07
    ening
    0.07
    ting
    0.07
    igu
    0.07
    ilities
    0.07
    ãĤīãģĽ
    0.07
    oday
    0.07
    ôi
    0.06
    Activations Density 0.007%

    No Known Activations