© 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. 63264
    Prev
    Next
    INDEX
    Explanations

    terms related to safety measures and protective actions

    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
    INGS
    -0.19
    ingu
    -0.18
    NESS
    -0.18
    à¹ĩà¸Ķ
    -0.17
    isbury
    -0.17
    aeper
    -0.17
    ipsis
    -0.17
    ibri
    -0.17
    munition
    -0.17
    enderit
    -0.16
    POSITIVE LOGITS
    ally
    0.84
    ary
    0.74
    al
    0.72
    ous
    0.61
    ian
    0.56
    ate
    0.53
    ality
    0.52
    ial
    0.51
    atic
    0.50
    ic
    0.47
    Activations Density 0.033%

    No Known Activations