© 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. 54540
    Prev
    Next
    INDEX
    Explanations

    references to living individuals within various contexts

    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
    ondon
    -0.06
    моÑĤ
    -0.06
    urf
    -0.06
    .scalablytyped
    -0.06
    ennon
    -0.06
    æīĵ
    -0.06
    ãĤ¤ãĥ¤
    -0.06
     Leban
    -0.06
    anda
    -0.06
    pend
    -0.06
    POSITIVE LOGITS
    ึà¸ĩ
    0.06
    ТÐŀ
    0.06
    675
    0.06
    SetBranch
    0.06
    osh
    0.06
     Affero
    0.06
     pon
    0.06
     Pon
    0.06
    Jak
    0.06
    akit
    0.06
    Activations Density 0.001%

    No Known Activations