© 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. 13538
    Prev
    Next
    INDEX
    Explanations

    references to items or elements related to online communities and content management

    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
     often
    -0.21
     alone
    -0.21
     itself
    -0.19
     oder
    -0.17
    often
    -0.17
    ube
    -0.16
    Often
    -0.16
    UBE
    -0.16
     overall
    -0.16
     Often
    -0.16
    POSITIVE LOGITS
     except
    0.67
    except
    0.62
     Except
    0.56
    Except
    0.54
    _except
    0.46
     кÑĢоме
    0.39
    	except
    0.39
     kromÄĽ
    0.28
     trừ
    0.27
    cept
    0.26
    Activations Density 0.136%

    No Known Activations