© 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. 63295
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantities or portions related to discussions about funding and investment

    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
    Enumerator
    -0.14
     atol
    -0.14
    ENC
    -0.14
    peg
    -0.13
    .scalablytyped
    -0.13
     PROGMEM
    -0.13
     Pry
    -0.13
    οÏģ
    -0.13
    aub
    -0.13
    urat
    -0.13
    POSITIVE LOGITS
     portion
    0.78
     part
    0.67
     portions
    0.58
    portion
    0.57
     parte
    0.50
     fraction
    0.45
     chunk
    0.43
    éĥ¨åĪĨ
    0.43
     parts
    0.41
     Portions
    0.40
    Activations Density 0.057%

    No Known Activations