© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 24027
    Prev
    Next
    INDEX
    Explanations

    words related to possession and characteristics

    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
    /or
    -0.17
    /from
    -0.15
    ila
    -0.14
    orex
    -0.14
     seus
    -0.14
    ali
    -0.14
    usal
    -0.14
    oth
    -0.13
    alien
    -0.13
    olly
    -0.13
    POSITIVE LOGITS
    (ed
    0.19
     neither
    0.17
    eses
    0.17
     characteristics
    0.16
    lew
    0.16
    None
    0.16
    çļĦæĺ¯
    0.15
    anova
    0.15
    ilities
    0.15
    isko
    0.14
    Activations Density 0.075%

    No Known Activations