© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    suffixes typically associated with process-oriented or transformative actions

    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
    ãĥ¬ãĤ¹
    -0.06
     kì
    -0.06
    kest
    -0.06
    Äįek
    -0.06
    æĬľ
    -0.06
    ợi
    -0.06
    Realm
    -0.06
    .§
    -0.06
    gün
    -0.06
    875
    -0.06
    POSITIVE LOGITS
    atab
    0.07
    naissance
    0.07
    ATAB
    0.06
    notif
    0.06
    akening
    0.06
    usc
    0.06
    .infinity
    0.06
     convers
    0.06
    847
    0.06
     re
    0.06
    Activations Density 0.019%

    No Known Activations