© 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. 30078
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative processes and voting dynamics

    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
    raž
    -0.16
    ometr
    -0.15
    _BLK
    -0.15
    estring
    -0.14
    eda
    -0.14
     Alias
    -0.14
     è»
    -0.14
    raison
    -0.14
    LOBAL
    -0.13
    nev
    -0.13
    POSITIVE LOGITS
     predicate
    0.18
    162
    0.16
     unser
    0.16
     prism
    0.16
    [,]
    0.15
     Proud
    0.15
    (ph
    0.15
     messaging
    0.15
    ÑĢен
    0.14
    [n
    0.14
    Activations Density 0.148%

    No Known Activations