© 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. 73815
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their variations

    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
    chwitz
    -0.07
    tml
    -0.07
    ãĤīãģĦ
    -0.07
    fir
    -0.07
    emax
    -0.06
    िवस
    -0.06
    баÑĩ
    -0.06
    adil
    -0.06
    ÏĦÏİ
    -0.06
    ControlEvents
    -0.06
    POSITIVE LOGITS
    reau
    0.07
     promised
    0.06
    esso
    0.06
    amento
    0.06
     Rebellion
    0.06
     needed
    0.06
     Exped
    0.06
     BR
    0.05
     Bureau
    0.05
    Ä°Åŀ
    0.05
    Activations Density 0.021%

    No Known Activations