© 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. 28594
    Prev
    Next
    INDEX
    Explanations

    expressions centering on personal assertiveness and the importance of self-perception

    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
    -many
    -0.14
     strerror
    -0.14
    de
    -0.14
    -den
    -0.13
     ÙĩÙĨاÙĥ
    -0.13
    æīįèĥ½
    -0.13
    there
    -0.13
     there
    -0.13
    du
    -0.13
    ctl
    -0.13
    POSITIVE LOGITS
     ultimately
    0.29
     Ultimately
    0.26
     what
    0.24
    Ultimately
    0.23
    åıªè¦ģ
    0.21
     miá»ħn
    0.20
     irrelevant
    0.20
    what
    0.20
     all
    0.19
     none
    0.19
    Activations Density 0.044%

    No Known Activations