© 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. 63402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    \grid
    -0.16
    #af
    -0.15
    ijke
    -0.14
     cứu
    -0.13
    #ac
    -0.13
    idUser
    -0.13
     addCriterion
    -0.13
    irut
    -0.13
    alion
    -0.12
    #aa
    -0.12
    POSITIVE LOGITS
    âĢ¦↵
    0.19
     âĢ¦↵
    0.15
    ...↵
    0.15
    ..↵
    0.14
    ("'"
    0.14
     ÅĻÃŃj
    0.13
    ÅĻÃŃzenÃŃ
    0.13
     [âĢ¦]↵
    0.13
     ____
    0.12
    ....↵
    0.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.