Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23138
    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
    â̦↵
    -0.18
    â̦”
    -0.16
     æ°
    -0.14
     Born
    -0.14
    Âłin
    -0.14
    â̦and
    -0.14
    â̦"
    -0.14
     â̦↵
    -0.14
    â̦the
    -0.13
    emez
    -0.13
    POSITIVE LOGITS
    /***/
    0.16
    esktop
    0.15
    ãĤ·ãĤ¢
    0.14
    lander
    0.14
    екÑĤи
    0.13
    ãģ¾ãģļ
    0.13
    ÑĥÑģÑĤа
    0.13
    اØ
    0.13
    ÐŁÐļ
    0.13
    usercontent
    0.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.