© 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 EvalsExportsAPI 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. 56222
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person pronoun "I" and related phrases indicating personal experiences or requests

    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
    asse
    -0.07
     Microsystems
    -0.07
     Barney
    -0.07
    asion
    -0.06
    aln
    -0.06
    mlx
    -0.06
    643
    -0.06
    adow
    -0.06
    ulg
    -0.06
     Adresse
    -0.06
    POSITIVE LOGITS
    enberg
    0.07
     consent
    0.07
     haz
    0.06
    ront
    0.06
    ikon
    0.06
    ÑĢог
    0.06
    ös
    0.06
     Ø¢ÛĮا
    0.06
     cascade
    0.06
    CONS
    0.06
    Activations Density 0.007%

    No Known Activations