© 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. 73034
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their associated actions

    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
    िà¤ĸ
    -0.07
    ég
    -0.07
     اÙĦرسÙħ
    -0.06
    agina
    -0.06
    leur
    -0.06
    WithMany
    -0.06
    antha
    -0.06
    tÃŃ
    -0.06
    اÙģÛĮ
    -0.06
    ória
    -0.06
    POSITIVE LOGITS
    azo
    0.07
    hek
    0.07
     McCabe
    0.06
     straw
    0.06
    acist
    0.06
    Discover
    0.06
    ycop
    0.06
     attend
    0.06
    kaar
    0.06
    407
    0.06
    Activations Density 0.025%

    No Known Activations