© 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. 63211
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal relationships or social interactions

    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
    ovÃŃ
    -0.16
    imd
    -0.15
    NAL
    -0.14
    linger
    -0.13
    arin
    -0.13
    andest
    -0.13
    enas
    -0.13
    elia
    -0.13
    .sax
    -0.13
     smr
    -0.12
    POSITIVE LOGITS
     identified
    0.44
     Identified
    0.39
    identified
    0.38
     whose
    0.37
     whom
    0.36
     identification
    0.34
     identify
    0.34
     ident
    0.33
    whose
    0.32
     who
    0.32
    Activations Density 0.066%

    No Known Activations