© 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. 23833
    Prev
    Next
    INDEX
    Explanations

    indicators of personal feelings and emotional responses

    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
    uib
    -0.16
     invis
    -0.16
    _SI
    -0.15
    STANCE
    -0.15
     Nz
    -0.15
    ottage
    -0.14
    licit
    -0.14
    jd
    -0.14
    599
    -0.14
     mies
    -0.14
    POSITIVE LOGITS
     und
    0.66
    Und
    0.57
     Und
    0.57
    und
    0.47
     unp
    0.43
     unf
    0.40
    UND
    0.38
    unda
    0.35
     unm
    0.29
    undi
    0.29
    Activations Density 0.056%

    No Known Activations