© 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. 79859
    Prev
    Next
    INDEX
    Explanations

    terms related to stimulating discussions or reactions

    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
    izable
    -0.07
    amer
    -0.07
    .Exists
    -0.07
    åĺ
    -0.07
    amework
    -0.07
    zw
    -0.07
     Äijặt
    -0.07
    ern
    -0.07
    iw
    -0.07
    icie
    -0.07
    POSITIVE LOGITS
     debate
    0.08
     a
    0.07
     an
    0.07
     discussion
    0.07
     interest
    0.07
    elman
    0.07
     debates
    0.07
     dormant
    0.07
    ONTAL
    0.07
     conversation
    0.07
    Activations Density 0.013%

    No Known Activations