© 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. 130443
    Prev
    Next
    INDEX
    Explanations

    dialogue expressing disbelief or confrontation

    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
    umpt
    -0.07
    cke
    -0.07
    isse
    -0.07
    ÙĪدÙĩ
    -0.07
     concess
    -0.07
    eldo
    -0.06
    league
    -0.06
    ignet
    -0.06
    ÑģÑĤиÑĤ
    -0.06
    StackTrace
    -0.06
    POSITIVE LOGITS
     tell
    0.09
    Tell
    0.08
     Tell
    0.08
    tell
    0.08
     telling
    0.08
     tells
    0.08
     seriously
    0.08
     argument
    0.07
     me
    0.07
     suggestion
    0.07
    Activations Density 0.024%

    No Known Activations