© 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. 73359
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and expressions of self-identity

    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
    ensch
    -0.08
    uve
    -0.07
    irut
    -0.07
    िण
    -0.06
    .getP
    -0.06
    zee
    -0.06
    aspers
    -0.06
    oulos
    -0.06
     Laur
    -0.06
    ollah
    -0.06
    POSITIVE LOGITS
     will
    0.14
    will
    0.12
    'll
    0.10
     WILL
    0.10
     sẽ
    0.10
    Will
    0.10
     akan
    0.10
     Will
    0.09
    ä¼ļ
    0.09
    ’ll
    0.09
    Activations Density 0.030%

    No Known Activations