© 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. 29991
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and cities

    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
    onth
    -0.15
    erti
    -0.15
    ormsg
    -0.15
    -purple
    -0.14
    .ly
    -0.14
    ngr
    -0.14
    iners
    -0.13
    agher
    -0.13
    à¹Ģà¸ķà¸Ńร
    -0.13
    rani
    -0.13
    POSITIVE LOGITS
    -based
    0.71
     based
    0.60
    based
    0.60
    _based
    0.54
    -Based
    0.54
     Based
    0.51
    Based
    0.50
    -base
    0.36
    åŁºäºİ
    0.35
     dá»±a
    0.33
    Activations Density 0.031%

    No Known Activations