© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    negations and critical remarks regarding actions or behaviors

    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
    ÑĤÑİ
    -0.17
    ink
    -0.14
    اÙģر
    -0.14
    еÑĤÑĮ
    -0.14
    asses
    -0.14
    ër
    -0.13
     Adrian
    -0.13
    inalg
    -0.13
     radiation
    -0.13
    ictions
    -0.12
    POSITIVE LOGITS
     attack
    1.26
     Attack
    1.14
     attacks
    1.09
    attack
    1.02
     attacked
    1.02
     ATTACK
    0.99
    Attack
    0.98
     attacking
    0.97
     Attacks
    0.95
     attackers
    0.91
    Activations Density 0.005%

    No Known Activations