© 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. 120804
    Prev
    Next
    INDEX
    Explanations

    references to perspective or ownership, especially using first-person pronouns

    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
    OfClass
    -0.09
    kı
    -0.07
    (:,:,
    -0.07
    ums
    -0.07
    аÑĤив
    -0.07
    kip
    -0.07
    κε
    -0.06
    lier
    -0.06
    #ad
    -0.06
    agento
    -0.06
    POSITIVE LOGITS
     aim
    0.13
     goal
    0.11
     hope
    0.09
     objective
    0.08
     intention
    0.08
     intent
    0.08
     priority
    0.08
    goal
    0.07
     plan
    0.07
     focus
    0.07
    Activations Density 0.023%

    No Known Activations