© 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 EvalsExportsinterp-engineNEWAPI 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. 62045
    Prev
    Next
    INDEX
    Explanations

    the word "question" and its variations, indicating inquiries or topics of discussion

    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
    ساÙĦ
    -0.06
    regnum
    -0.06
    ish
    -0.06
    VERTISEMENT
    -0.06
     anlamda
    -0.06
    obus
    -0.06
    ick
    -0.06
     Glo
    -0.06
    ãĤ«ãĥ¼
    -0.06
    ican
    -0.06
    POSITIVE LOGITS
    gnore
    0.08
    oÄŁ
    0.07
    ÑĨип
    0.07
    clar
    0.07
    ably
    0.07
    kaar
    0.07
    erras
    0.07
    erval
    0.07
     kå
    0.06
    ioned
    0.06
    Activations Density 0.008%

    No Known Activations