© 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. 30110
    Prev
    Next
    INDEX
    Explanations

    references to semi-automatic firearms

    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
    enan
    -0.16
    ÙĨا
    -0.15
    bt
    -0.14
    enburg
    -0.14
    @student
    -0.14
    edir
    -0.14
    воÑİ
    -0.13
    bal
    -0.13
    oggle
    -0.13
    rev
    -0.13
    POSITIVE LOGITS
     semi
    0.28
     Semi
    0.26
    esters
    0.23
    aphore
    0.21
    -finals
    0.20
    semi
    0.20
    annual
    0.20
    (sem
    0.20
    ãĥĬãĥ¼
    0.19
    antics
    0.19
    Activations Density 0.006%

    No Known Activations