© 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. 29962
    Prev
    Next
    INDEX
    Explanations

    indicators of personal beliefs and societal attitudes

    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
     èĩªåĬ¨çĶŁæĪIJ
    -0.17
    idar
    -0.16
    lub
    -0.15
    arella
    -0.14
    ãĥ¼ãĥ³
    -0.14
    ÑĪев
    -0.13
    або
    -0.13
     èĴ
    -0.13
    esta
    -0.13
    ainers
    -0.13
    POSITIVE LOGITS
    35
    0.20
    25
    0.19
    28
    0.18
    29
    0.18
    30
    0.16
    32
    0.16
    27
    0.15
    23
    0.15
    22
    0.15
    26
    0.15
    Activations Density 0.038%

    No Known Activations