© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89580
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" and its variations, suggesting a focus on personal experiences or actions

    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
    omy
    -0.07
    ÙĪÙĨد
    -0.07
     McLaren
    -0.07
     zwar
    -0.07
    ond
    -0.07
    Å¡t
    -0.07
    sthrough
    -0.06
    acht
    -0.06
    abant
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
     ever
    0.07
    åĢij
    0.07
    zb
    0.07
     respective
    0.06
     became
    0.06
    ureka
    0.06
     succ
    0.06
    EN
    0.06
     any
    0.06
    eding
    0.06
    Activations Density 0.017%

    No Known Activations