© 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. 108199
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive adjectives

    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
    raya
    -0.09
    ãĤıãģij
    -0.08
    ãģªãģĮ
    -0.08
    èm
    -0.08
    ÑĢива
    -0.07
    ernen
    -0.07
    nitÅĻ
    -0.07
    人æīį
    -0.07
     ustanov
    -0.07
     Ãĸr
    -0.07
    POSITIVE LOGITS
     own
    0.07
     similarly
    0.06
     NSS
    0.06
    essor
    0.05
     separately
    0.05
     ebenfalls
    0.05
     Sne
    0.05
    itch
    0.05
     Maul
    0.05
     RSVP
    0.05
    Activations Density 0.043%

    No Known Activations