© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 33106
    Prev
    Next
    INDEX
    Explanations

    words related to performance evaluation and skills in a competitive context

    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
    agem
    -0.15
    stab
    -0.15
    جÙĪ
    -0.14
     fır
    -0.14
    ĺIJ
    -0.14
     stakes
    -0.13
    à¸Ħำ
    -0.13
    ssel
    -0.13
     Bowman
    -0.13
    ivo
    -0.13
    POSITIVE LOGITS
     lift
    0.39
     lifts
    0.38
     lifting
    0.35
    lift
    0.33
     Lift
    0.33
    lifting
    0.32
     squat
    0.30
     lifted
    0.28
     Bench
    0.27
     strength
    0.27
    Activations Density 0.033%

    No Known Activations