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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9257
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate a relationship between two entities, particularly in terms of value or significance

    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
     indirect
    -0.16
     equally
    -0.15
     Bord
    -0.15
    dish
    -0.14
    allon
    -0.14
     INDIRECT
    -0.14
    .nan
    -0.14
     indirectly
    -0.13
    SystemService
    -0.13
    _PROXY
    -0.13
    POSITIVE LOGITS
     anything
    0.33
    anything
    0.29
     Anything
    0.26
    Anything
    0.26
     actual
    0.23
    actual
    0.21
    oy
    0.18
    ibrator
    0.18
    ught
    0.18
    (actual
    0.17
    Activations Density 0.018%

    No Known Activations