© 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. 54364
    Prev
    Next
    INDEX
    Explanations

    negative descriptors or judgments regarding people and ideas

    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
    ÅĻen
    -0.17
     ugl
    -0.16
    ácil
    -0.16
     RedirectTo
    -0.15
    endale
    -0.15
    erator
    -0.15
    imen
    -0.14
    strup
    -0.14
    atile
    -0.14
    MOTE
    -0.14
    POSITIVE LOGITS
    /or
    0.22
     clue
    0.17
     mean
    0.15
     Shorts
    0.15
    obb
    0.15
    rog
    0.15
     il
    0.14
     downright
    0.14
     shorts
    0.14
     Mean
    0.14
    Activations Density 0.115%

    No Known Activations