© 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. 86644
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns expressing personal experience or sentiment

    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
    amina
    -0.06
    arna
    -0.06
    issen
    -0.06
     поÑģ
    -0.06
    à¸ĵà¸ij
    -0.06
    aul
    -0.06
     chalk
    -0.06
    .Constants
    -0.06
    ahan
    -0.06
    _binding
    -0.06
    POSITIVE LOGITS
    elong
    0.07
    uess
    0.07
    young
    0.06
    \admin
    0.06
    theid
    0.06
    abler
    0.06
    rit
    0.06
    iche
    0.06
     trusts
    0.06
    771
    0.06
    Activations Density 0.006%

    No Known Activations