© 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. 38787
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal experiences or preferences

    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
    vironment
    -0.07
     ange
    -0.07
    еÑĢб
    -0.07
    posure
    -0.06
    Ñħи
    -0.06
    æĢĿãģĦ
    -0.06
    islav
    -0.06
    baum
    -0.06
    ÑĢен
    -0.06
    hip
    -0.06
    POSITIVE LOGITS
     personally
    0.09
    riad
    0.08
     usually
    0.08
     often
    0.07
     suggest
    0.07
     bazen
    0.07
    iselect
    0.07
     Recomm
    0.06
     typically
    0.06
    awai
    0.06
    Activations Density 0.025%

    No Known Activations