© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    references to family relationships

    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
    zia
    -0.07
    çķĮ
    -0.06
    edia
    -0.06
    ayne
    -0.06
    eing
    -0.06
    #{@
    -0.06
    ãĢ
    -0.06
     Plants
    -0.06
    ogn
    -0.05
    yonel
    -0.05
    POSITIVE LOGITS
    -in
    0.07
    ousand
    0.07
    adow
    0.07
    [url
    0.07
    orean
    0.07
    enz
    0.06
     lesser
    0.06
    izo
    0.06
    atters
    0.06
    Ŀ
    0.06
    Activations Density 0.015%

    No Known Activations