© 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. 54764
    Prev
    Next
    INDEX
    Explanations

    actions and behaviors related to governance and conduct

    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
    .tap
    -0.21
    ÏĩεδÏĮν
    -0.16
    à¸Ķย
    -0.15
    íĻľëıĻ
    -0.15
    å¿ĥéĩĮ
    -0.15
    ngör
    -0.14
    kaar
    -0.14
    _intr
    -0.14
    _detalle
    -0.14
    ahoo
    -0.14
    POSITIVE LOGITS
     towards
    0.45
     during
    0.43
     regarding
    0.40
     toward
    0.40
     vis
    0.35
    during
    0.33
     During
    0.30
     concerning
    0.29
     Towards
    0.29
     when
    0.28
    Activations Density 0.055%

    No Known Activations