© 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. 41264
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and contact information

    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
    apis
    -0.17
    Äĥng
    -0.14
    Äįek
    -0.14
    ìĿ¸íĬ¸
    -0.14
    cion
    -0.14
    isku
    -0.13
    APPING
    -0.13
    aed
    -0.13
    Ñĥнк
    -0.13
    emez
    -0.13
    POSITIVE LOGITS
     O
    0.50
     Ðŀ
    0.38
     à¤ĵ
    0.35
    .O
    0.35
    _O
    0.33
    O
    0.32
     ãĤª
    0.32
    ãĤª
    0.31
     o
    0.31
    -O
    0.30
    Activations Density 0.075%

    No Known Activations