© 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. 124019
    Prev
    Next
    INDEX
    Explanations

    scenes involving conflict or tension in various settings

    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
    ardash
    -0.08
    apo
    -0.08
    agner
    -0.08
    hta
    -0.08
    Ñĥ
    -0.07
    uchi
    -0.07
    ornado
    -0.07
    odus
    -0.07
    adelphia
    -0.07
    thetic
    -0.06
    POSITIVE LOGITS
    657
    0.07
    utz
    0.07
     Caldwell
    0.07
     grosse
    0.07
    .DOM
    0.07
    065
    0.06
    ijn
    0.06
    pel
    0.06
    ÏĮδ
    0.06
    CASCADE
    0.06
    Activations Density 0.017%

    No Known Activations