© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41750
    Prev
    Next
    INDEX
    Explanations

    expressions related to perception and evaluation of situations or entities

    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
    oron
    -0.17
    onia
    -0.17
    ongan
    -0.15
    ì¹´ëĿ¼
    -0.15
     discreet
    -0.15
    uum
    -0.14
    sher
    -0.14
    eties
    -0.14
    åĬ¹
    -0.14
    _Ref
    -0.14
    POSITIVE LOGITS
     like
    0.31
    _like
    0.23
    like
    0.23
     promising
    0.22
     Like
    0.20
     likes
    0.20
    .like
    0.20
     alike
    0.20
    Like
    0.20
    åĥıæĺ¯
    0.19
    Activations Density 0.035%

    No Known Activations