© 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. 74212
    Prev
    Next
    INDEX
    Explanations

    statements or questions expressing certainty or insistence

    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
    semantic
    -0.07
     fkk
    -0.07
    CDATA
    -0.07
     delt
    -0.07
     sche
    -0.07
    pio
    -0.07
     slee
    -0.07
    abal
    -0.07
    INSTALL
    -0.07
    UTO
    -0.07
    POSITIVE LOGITS
    lyn
    0.06
     Mein
    0.06
    noinspection
    0.06
     cá
    0.06
     Hamp
    0.06
     HCI
    0.05
    /*******************************************************************************↵
    0.05
    vertis
    0.05
     Telescope
    0.05
    ائÙĦ
    0.05
    Activations Density 0.000%

    No Known Activations