© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 42018
    Prev
    Next
    INDEX
    Explanations

    actions and concepts related to negotiation and economic transactions

    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
     various
    -0.16
     Bazı
    -0.15
    æľĢè¿ij
    -0.14
    äºĽ
    -0.14
     many
    -0.14
    ingga
    -0.14
    ÑĤоÑĩ
    -0.14
    many
    -0.13
    OME
    -0.13
    jÃŃm
    -0.13
    POSITIVE LOGITS
     someone
    0.43
     something
    0.42
     such
    0.39
    someone
    0.35
    something
    0.35
    ä¸Ģ个
    0.35
     somebody
    0.34
     an
    0.32
    such
    0.32
     a
    0.32
    Activations Density 0.325%

    No Known Activations