© 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 EvalsExportsinterp-engineNEWAPI 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. 13595
    Prev
    Next
    INDEX
    Explanations

    mentions of visual media presentations and descriptions of actions involving sharp objects

    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
     just
    -0.15
    agger
    -0.14
     nearly
    -0.13
    _should
    -0.13
    ufe
    -0.13
    ugen
    -0.13
     actually
    -0.12
    427
    -0.12
    :href
    -0.12
    avez
    -0.12
    POSITIVE LOGITS
     unknown
    0.52
    unknown
    0.45
     Unknown
    0.43
    Unknown
    0.43
     UNKNOWN
    0.42
     unspecified
    0.39
    UNKNOWN
    0.38
    .unknown
    0.38
    _unknown
    0.38
     unidentified
    0.37
    Activations Density 0.011%

    No Known Activations