© 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. 4846
    Prev
    Next
    INDEX
    Explanations

    instances of character dialogue and speech 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
    :↵↵↵↵
    -0.07
    benh
    -0.07
    zon
    -0.06
    efon
    -0.06
    neau
    -0.06
    hoff
    -0.06
    /MPL
    -0.06
    uchs
    -0.06
    ÙĨاÙĨ
    -0.06
    :↵↵↵
    -0.06
    POSITIVE LOGITS
    rena
    0.06
     emphasis
    0.06
    dde
    0.06
     swallow
    0.06
     tw
    0.05
    #endregion
    0.05
    dds
    0.05
     gri
    0.05
    Í
    0.05
     balance
    0.05
    Activations Density 0.021%

    No Known Activations