© 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. 33118
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and phrases indicating quantities or lists related to interest in a project

    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
    instanc
    -0.14
    iled
    -0.14
    uong
    -0.14
    åĩī
    -0.14
    JsonValue
    -0.14
    iqueta
    -0.13
    æĺĩ
    -0.13
    liš
    -0.13
    ragments
    -0.13
    λικ
    -0.13
    POSITIVE LOGITS
     pre
    0.57
     reserve
    0.48
     reservation
    0.48
     reservations
    0.44
     Reserve
    0.44
     reserved
    0.42
     Pre
    0.41
     reserves
    0.41
     Reservation
    0.38
     preorder
    0.37
    Activations Density 0.026%

    No Known Activations