© 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. 29281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or development based on prior success or foundations

    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
     bekl
    -0.17
     odst
    -0.15
    HeaderCode
    -0.14
    isContained
    -0.14
    faces
    -0.14
    hani
    -0.14
    illac
    -0.13
    viar
    -0.13
    eprom
    -0.13
    allis
    -0.13
    POSITIVE LOGITS
     foundation
    0.64
     foundations
    0.52
     base
    0.52
    foundation
    0.45
     groundwork
    0.42
    base
    0.41
     Foundation
    0.40
    åŁºç¡Ģ
    0.40
    Foundation
    0.37
     bases
    0.35
    Activations Density 0.034%

    No Known Activations