© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 42323
    Prev
    Next
    INDEX
    Explanations

    references to discussions about political figures and authority

    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
    itti
    -0.14
    ctp
    -0.14
    ãĥ«ãĤ¯
    -0.14
    itet
    -0.14
    â̦.↵↵
    -0.14
    ierz
    -0.13
    astes
    -0.13
    .mu
    -0.13
    anto
    -0.13
    ColumnsMode
    -0.13
    POSITIVE LOGITS
    201
    0.23
     Hispanic
    0.14
    Periph
    0.14
     MMI
    0.14
    ìĿ¼
    0.13
    æĻĵ
    0.13
     setuptools
    0.13
    ufig
    0.12
    ÏĦαι
    0.12
    ountains
    0.12
    Activations Density 0.032%

    No Known Activations