© 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. 130406
    Prev
    Next
    INDEX
    Explanations

    the word "me" used in various contexts, often reflecting personal perspectives or feelings

    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
    umer
    -0.07
    oto
    -0.07
    yne
    -0.07
     quoi
    -0.07
     ked
    -0.07
    eft
    -0.07
    kening
    -0.06
    ulaire
    -0.06
    lse
    -0.06
    isse
    -0.06
    POSITIVE LOGITS
     rằng
    0.08
    ackle
    0.07
    cape
    0.07
    ivi
    0.06
    ately
    0.06
    AutoSize
    0.06
     personally
    0.06
    /javascript
    0.06
    clide
    0.06
    akin
    0.06
    Activations Density 0.005%

    No Known Activations