© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and organizations

    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
    iants
    -0.07
    rijk
    -0.07
    errupted
    -0.07
    cura
    -0.07
    oppable
    -0.06
    primir
    -0.06
    znik
    -0.06
    chalk
    -0.06
    few
    -0.06
    atrix
    -0.06
    POSITIVE LOGITS
    ess
    0.09
    erness
    0.08
    iliary
    0.07
    wel
    0.07
    aked
    0.07
    vil
    0.07
    sd
    0.07
    est
    0.07
    iversal
    0.06
    ιά
    0.06
    Activations Density 0.001%

    No Known Activations