© 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. 15318
    Prev
    Next
    INDEX
    Explanations

    words associated with excitement and thrill-seeking activities

    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
    liness
    -0.07
    em
    -0.07
    .au
    -0.07
    ech
    -0.07
    ypse
    -0.07
    eper
    -0.07
    име
    -0.07
    eming
    -0.07
    ev
    -0.06
    emens
    -0.06
    POSITIVE LOGITS
    ingly
    0.14
    ington
    0.10
    .Tasks
    0.08
    viso
    0.08
    INGTON
    0.07
    wave
    0.07
    ursday
    0.07
    pants
    0.07
    fully
    0.07
    ousand
    0.07
    Activations Density 0.005%

    No Known Activations