© 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. 62014
    Prev
    Next
    INDEX
    Explanations

    sections or headings in news articles

    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
    ERIC
    -0.07
    ÑĪÑĮ
    -0.06
    avad
    -0.06
    585
    -0.06
    arro
    -0.06
    lest
    -0.06
    sg
    -0.06
    obia
    -0.06
    ilet
    -0.06
    prd
    -0.06
    POSITIVE LOGITS
     damer
    0.07
     thÃŃ
    0.06
    IPA
    0.06
    misc
    0.06
    Č↵
    0.06
    midd
    0.06
    raquo
    0.06
    >tag
    0.06
    pson
    0.06
    αλλ
    0.06
    Activations Density 0.012%

    No Known Activations