© 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. 105053
    Prev
    Next
    INDEX
    Explanations

    various forms of entertainment and live performances

    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
    uce
    -0.07
    isser
    -0.07
    .SizeMode
    -0.07
    è·
    -0.06
    ulta
    -0.06
    hone
    -0.06
    anner
    -0.06
    seealso
    -0.06
    奴
    -0.06
     vidé
    -0.06
    POSITIVE LOGITS
    viewer
    0.07
    Viewer
    0.07
     performance
    0.07
     tickets
    0.07
    mes
    0.07
     attraction
    0.07
     show
    0.07
     stools
    0.07
     performances
    0.07
    alen
    0.07
    Activations Density 0.005%

    No Known Activations