© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 78433
    Prev
    Next
    INDEX
    Explanations

    phrases related to initiation or commencement

    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
    ses
    -0.07
    appings
    -0.07
    ìĦľ
    -0.07
    á»iji
    -0.07
    ansson
    -0.07
    llib
    -0.07
    ouro
    -0.07
    ouch
    -0.07
    ilha
    -0.06
    ARSER
    -0.06
    POSITIVE LOGITS
    ly
    0.07
    LY
    0.06
    tom
    0.06
    tod
    0.06
    etty
    0.06
    tik
    0.06
    Ïģά
    0.06
    äºİ
    0.06
    RGBA
    0.06
    .mx
    0.05
    Activations Density 0.007%

    No Known Activations