© 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 EvalsExportsinterp-engineNEWAPI 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. 43863
    Prev
    Next
    INDEX
    Explanations

    mentions of intentional actions and the consequences of decisions

    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
    ngör
    -0.14
    ANGLES
    -0.14
    orre
    -0.14
    á»ģ
    -0.13
    HX
    -0.13
    oi
    -0.13
    anford
    -0.13
    ONGL
    -0.12
    aupt
    -0.12
    [email
    -0.12
    POSITIVE LOGITS
     act
    0.85
     actions
    0.84
     action
    0.78
     acts
    0.78
     Actions
    0.64
    actions
    0.64
    acts
    0.60
     ACTIONS
    0.59
    act
    0.59
    -actions
    0.58
    Activations Density 0.084%

    No Known Activations