© 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. 117148
    Prev
    Next
    INDEX
    Explanations

    elements of conflict and tension in narratives

    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
    chw
    -0.09
    erap
    -0.09
    ientes
    -0.08
    ÅĻes
    -0.08
    znik
    -0.08
     Ãĸn
    -0.08
    kea
    -0.07
    strftime
    -0.07
    vanished
    -0.07
    inç
    -0.07
    POSITIVE LOGITS
     kill
    0.10
     killing
    0.09
     kills
    0.08
     killed
    0.07
     execution
    0.07
     deaths
    0.07
     mission
    0.07
    kill
    0.06
     save
    0.06
     target
    0.06
    Activations Density 0.019%

    No Known Activations