© 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. 128802
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the use of the first-person pronoun "I."

    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
    lopen
    -0.08
    bilt
    -0.08
    áp
    -0.08
     itself
    -0.07
    bidden
    -0.07
    ارس
    -0.07
    gether
    -0.07
    ousand
    -0.07
    lx
    -0.07
    ENAME
    -0.07
    POSITIVE LOGITS
    ’m
    0.11
    'm
    0.11
    've
    0.10
    ’ve
    0.09
     myself
    0.09
     am
    0.09
    zzo
    0.09
    'll
    0.09
     бÑĥдÑĥ
    0.08
    zelf
    0.08
    Activations Density 0.115%

    No Known Activations