© 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. 42833
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or uncertainty

    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
     themselves
    -0.18
    istas
    -0.17
    hn
    -0.15
    agn
    -0.15
    itol
    -0.15
     Latter
    -0.14
    &action
    -0.14
    atz
    -0.14
    cia
    -0.14
    иÑģÑĤ
    -0.13
    POSITIVE LOGITS
     raining
    0.25
     happen
    0.22
    rain
    0.20
     beh
    0.20
     matter
    0.20
     dawn
    0.19
     happened
    0.19
     Happ
    0.19
     impossible
    0.18
    matter
    0.18
    Activations Density 0.148%

    No Known Activations