© 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. 9205
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with financial aid and resources

    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
    jspx
    -0.17
    lod
    -0.15
    seys
    -0.15
    ãģĵãĤĵãģ«
    -0.15
    ÑĢаÑĩ
    -0.15
    /Dk
    -0.14
    emouth
    -0.14
    .Apis
    -0.14
    reater
    -0.14
    Ñĩин
    -0.14
    POSITIVE LOGITS
     actionTypes
    0.15
     Ledger
    0.14
     d
    0.13
    ÅĽci
    0.13
     s
    0.13
     n
    0.13
    OV
    0.13
    ath
    0.12
     superv
    0.12
    \Eloquent
    0.12
    Activations Density 0.112%

    No Known Activations