© 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. 9064
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    âĢ¦↵
    -0.18
     âĢ¦↵
    -0.14
    âĢ¦”
    -0.13
    -&
    -0.13
    âĢ¦↵↵
    -0.13
    âĢ¦"
    -0.13
    eration
    -0.13
     Crew
    -0.12
    arshal
    -0.12
    Lorem
    -0.12
    POSITIVE LOGITS
    wed
    0.14
    .yahoo
    0.14
    uin
    0.14
    ød
    0.13
    =-=-=-=-=-=-=-=-
    0.13
    ivec
    0.13
    ëĵľë¦¬
    0.13
    yk
    0.13
    hled
    0.13
    ertools
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.