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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9147
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and self-association with specific labels or groups

    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
    iol
    -0.15
    imas
    -0.14
     Zur
    -0.14
    TAIL
    -0.13
    igne
    -0.13
    cir
    -0.13
     overhe
    -0.13
    opp
    -0.13
     recognize
    -0.13
     Sass
    -0.13
    POSITIVE LOGITS
    ableView
    0.21
     associated
    0.18
    associated
    0.17
    RIA
    0.17
     createContext
    0.17
    -associated
    0.16
    asso
    0.16
    째
    0.15
     Identified
    0.15
     ìĶ¨
    0.15
    Activations Density 0.011%

    No Known Activations