© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28272
    Prev
    Next
    INDEX
    Explanations

    strong declarative statements or opinions followed by supporting evidence or qualifications

    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
     therefore
    -0.23
    Therefore
    -0.21
     Therefore
    -0.19
     thus
    -0.18
     instead
    -0.17
    thus
    -0.17
    Thus
    -0.16
    instead
    -0.16
     despite
    -0.16
    Äįná
    -0.16
    POSITIVE LOGITS
     but
    0.61
     But
    0.47
    but
    0.47
     nhưng
    0.44
     BUT
    0.43
    But
    0.43
     pero
    0.41
     но
    0.40
     maar
    0.39
    ï¼Įä½Ĩ
    0.38
    Activations Density 0.298%

    No Known Activations