© 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. 55592
    Prev
    Next
    INDEX
    Explanations

    expressions related to commitment and dedication

    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
    aban
    -0.07
    ala
    -0.07
    abit
    -0.07
    fid
    -0.07
    zano
    -0.06
     Fior
    -0.06
    deaux
    -0.06
    ç«ĭãģ¦
    -0.06
    @js
    -0.06
    eca
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    meli
    0.06
    aster
    0.06
    iffe
    0.06
    ом
    0.06
    Slf
    0.06
    ythe
    0.06
    ách
    0.06
    .only
    0.06
     Souls
    0.06
    Activations Density 0.000%

    No Known Activations