© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54419
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistical data or probabilities

    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
    ernet
    -0.16
    ÅĻel
    -0.14
    ycop
    -0.12
    åĭĴ
    -0.12
    .radioButton
    -0.12
    din
    -0.11
    ç§Ģ
    -0.11
    -that
    -0.11
     wiÄĻc
    -0.11
    ãĥ¼ãĤ
    -0.11
    POSITIVE LOGITS
     etc
    0.21
     ÑĤоÑīо
    0.15
     respectively
    0.14
    .bunifuFlatButton
    0.14
    etc
    0.14
    ÑĢониÑĩеÑģ
    0.14
    бÑĥдÑĮ
    0.13
    ãĤ¤ãĥ³ãĥĪ
    0.13
     ÃĤ
    0.13
    stery
    0.13
    Activations Density 0.029%

    No Known Activations