© 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. 13360
    Prev
    Next
    INDEX
    Explanations

    references to community events and social networking

    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
    yne
    -0.14
    lut
    -0.14
     unlike
    -0.14
    ube
    -0.13
    ooke
    -0.13
     butterfly
    -0.13
    ina
    -0.13
    ertas
    -0.13
     butter
    -0.12
     Butterfly
    -0.12
    POSITIVE LOGITS
     except
    0.92
    except
    0.82
     Except
    0.79
    Except
    0.76
    _except
    0.55
    	except
    0.51
     minus
    0.51
     but
    0.47
    minus
    0.46
     only
    0.42
    Activations Density 0.080%

    No Known Activations