© 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. 63417
    Prev
    Next
    INDEX
    Explanations

    terms related to conducting investigations or analyses

    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
    Ñģол
    -0.16
    /Instruction
    -0.15
    /umd
    -0.14
    awai
    -0.14
    à¹ģรà¸ĩ
    -0.13
    รรà¸Ħ
    -0.13
    çĩ
    -0.13
    occo
    -0.13
    ÙĪت
    -0.13
    [opt
    -0.13
    POSITIVE LOGITS
     tests
    0.30
     studies
    0.30
     analysis
    0.30
     research
    0.27
     thorough
    0.26
     investigation
    0.25
     extensive
    0.25
     investigations
    0.25
     testing
    0.24
     analyses
    0.24
    Activations Density 0.199%

    No Known Activations