© 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. 29150
    Prev
    Next
    INDEX
    Explanations

    rankings and positions in competitive contexts

    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
    pent
    -0.15
    otope
    -0.14
    callee
    -0.14
    arts
    -0.14
     addCriterion
    -0.14
    ázev
    -0.13
    parer
    -0.13
     zo
    -0.13
    rix
    -0.13
    cdecl
    -0.13
    POSITIVE LOGITS
     players
    1.04
     player
    1.01
     Players
    0.91
     Player
    0.84
    Players
    0.77
    players
    0.77
    player
    0.76
    -player
    0.76
    Player
    0.75
    _player
    0.70
    Activations Density 0.013%

    No Known Activations