© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 44953
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person singular pronoun "I" and related verb forms indicating personal expression or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reck
    -0.18
     sworn
    -0.15
    die
    -0.14
    èo
    -0.14
    edback
    -0.14
    ENAME
    -0.14
     geschichten
    -0.13
    Occurred
    -0.13
    tas
    -0.13
    SWEP
    -0.13
    POSITIVE LOGITS
     am
    0.31
     myself
    0.30
    ’m
    0.21
    'm
    0.21
     personally
    0.18
    -am
    0.18
     have
    0.18
    've
    0.18
    ’ve
    0.16
     must
    0.16
    Activations Density 0.396%

    No Known Activations