© 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. 124683
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or groups of people

    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
    oÄŁ
    -0.07
    à¥Īà¤ļ
    -0.07
    484
    -0.07
    baÅŁ
    -0.07
    меж
    -0.07
    cury
    -0.07
    ój
    -0.07
    æľ¬
    -0.07
    ze
    -0.07
    illac
    -0.07
    POSITIVE LOGITS
     Gregg
    0.07
    eyer
    0.06
     Ley
    0.06
    unks
    0.06
     st
    0.06
    ãĥŃãĥ¼
    0.06
     anonymously
    0.06
    IFI
    0.06
    afe
    0.06
    ses
    0.05
    Activations Density 0.002%

    No Known Activations