© 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. 71329
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions expressing disbelief or emphasis

    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
    edith
    -0.07
    loub
    -0.07
    estion
    -0.07
    oleon
    -0.07
    stash
    -0.07
    ÑĥÑĩа
    -0.07
     sic
    -0.07
    ĶĶ
    -0.06
     forth
    -0.06
    _PID
    -0.06
    POSITIVE LOGITS
    rez
    0.07
     arrow
    0.06
    bs
    0.06
    agh
    0.06
    ault
    0.06
    pek
    0.06
     Freed
    0.06
    izo
    0.06
     interesting
    0.06
    610
    0.05
    Activations Density 0.006%

    No Known Activations