© 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. 41663
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or wanting

    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
    Ùĩ
    -0.17
    #af
    -0.16
    ÑĢÑıд
    -0.15
    indh
    -0.15
    pery
    -0.14
    èħķ
    -0.14
    алÑİ
    -0.14
    _intent
    -0.14
    Å©
    -0.14
    /*č↵
    -0.13
    POSITIVE LOGITS
     to
    0.26
    only
    0.25
    ted
    0.19
     nothing
    0.18
    t
    0.17
    tion
    0.17
    ç´ł
    0.17
    lessly
    0.17
    efully
    0.17
    eful
    0.15
    Activations Density 0.010%

    No Known Activations