© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12391
    Prev
    Next
    INDEX
    Explanations

    descriptors related to environmental conditions and deteriorating structures

    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
    orta
    -0.15
    asso
    -0.14
    _cast
    -0.14
     twink
    -0.14
    ¶Į
    -0.14
    ses
    -0.13
     pari
    -0.13
    agnost
    -0.13
    areth
    -0.13
    erson
    -0.13
    POSITIVE LOGITS
    -gray
    0.17
    bulk
    0.16
    -looking
    0.16
    neas
    0.15
    -green
    0.15
     bulk
    0.15
    -white
    0.15
     depths
    0.14
    redients
    0.14
    OKIE
    0.14
    Activations Density 0.217%

    No Known Activations