© 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 EvalsExportsAPI 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. 29380
    Prev
    Next
    INDEX
    Explanations

    actions and achievements related to performances, awards, and collaborations in the arts

    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
    allee
    -0.07
    acas
    -0.06
    cio
    -0.06
    .xz
    -0.06
    idal
    -0.06
    imbledon
    -0.06
    redits
    -0.06
    ession
    -0.06
    stal
    -0.06
    CHR
    -0.06
    POSITIVE LOGITS
    otto
    0.07
     Revel
    0.06
     McB
    0.06
     impulses
    0.06
    ango
    0.06
     Moder
    0.06
    INESS
    0.06
    ovies
    0.05
    harma
    0.05
    LOS
    0.05
    Activations Density 0.092%

    No Known Activations