© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 29759
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and competition

    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
    eriod
    -0.19
    onec
    -0.17
    _mE
    -0.16
     salope
    -0.15
    astle
    -0.15
     nackte
    -0.15
    esser
    -0.15
    sects
    -0.15
    _mD
    -0.15
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    -0.15
    POSITIVE LOGITS
    (s
    0.28
    (es
    0.20
    (
    0.17
    iotic
    0.15
    576
    0.15
    0.15
    tings
    0.14
    .netflix
    0.14
     mod
    0.14
    undred
    0.14
    Activations Density 0.047%

    No Known Activations