© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43161
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or codes associated with articles and content references

    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
    omon
    -0.17
    ÅĻet
    -0.15
    aid
    -0.13
    ..:
    -0.13
    abor
    -0.13
    .ff
    -0.12
    lero
    -0.12
     diaper
    -0.12
    ecial
    -0.12
    .UIManager
    -0.12
    POSITIVE LOGITS
    raki
    0.14
    xxx
    0.14
    94
    0.13
    osaic
    0.13
    93
    0.13
    _WARNINGS
    0.13
    .scalablytyped
    0.13
    åķ
    0.13
    uled
    0.13
    ugs
    0.13
    Activations Density 0.162%

    No Known Activations