© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 43323
    Prev
    Next
    INDEX
    Explanations

    references to measurement or evaluation

    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
    akens
    -0.16
    527
    -0.14
    ecta
    -0.14
    ISM
    -0.14
    ass
    -0.14
    á»ģ
    -0.14
    zÄħd
    -0.14
    clair
    -0.13
     nit
    -0.13
     flagship
    -0.13
    POSITIVE LOGITS
     scales
    0.84
     scale
    0.74
     Scale
    0.68
    scale
    0.62
    Scale
    0.61
    cales
    0.59
     weigh
    0.58
     SCALE
    0.56
    -scale
    0.55
     weighing
    0.54
    Activations Density 0.008%

    No Known Activations