© 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. 15152
    Prev
    Next
    INDEX
    Explanations

    frequency-related terms or phrases

    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
    etsk
    -0.07
    atron
    -0.07
    ulfill
    -0.07
    antor
    -0.07
    IFT
    -0.06
    erge
    -0.06
    .AP
    -0.06
    usercontent
    -0.06
    scoped
    -0.06
    ÙĦÙĬÙĩ
    -0.06
    POSITIVE LOGITS
    clus
    0.06
     Svg
    0.06
    astro
    0.06
     exclusively
    0.06
    ÏĥÏĦÏģο
    0.06
     day
    0.06
    world
    0.05
    _deploy
    0.05
    ETERS
    0.05
    esting
    0.05
    Activations Density 0.001%

    No Known Activations