Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29293
    Prev
    Next
    INDEX
    Explanations

    references to the concept of holiness

    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
    icz
    -0.16
    dash
    -0.15
    nable
    -0.15
    arah
    -0.15
    nx
    -0.15
    sid
    -0.14
    ement
    -0.14
    nement
    -0.14
    à¤Ĺल
    -0.14
     Cobra
    -0.14
    POSITIVE LOGITS
    ocaust
    0.23
     Hol
    0.22
     hol
    0.21
    iness
    0.19
    omorphic
    0.18
    istic
    0.18
    Hol
    0.17
    mium
    0.17
    izontal
    0.17
     sway
    0.17
    Activations Density 0.007%

    No Known Activations