Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 38
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or critical assessments regarding situations

    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
    vig
    -0.16
    vinc
    -0.15
    gid
    -0.14
    anela
    -0.13
    945
    -0.13
    ÄĻż
    -0.13
     вп
    -0.12
    iaux
    -0.12
    xAE
    -0.12
    BOSE
    -0.12
    POSITIVE LOGITS
     timing
    0.90
     Timing
    0.81
    Timing
    0.73
    timing
    0.71
     timings
    0.58
     timed
    0.54
    _timing
    0.50
    .timing
    0.42
     timely
    0.41
     TIM
    0.38
    Activations Density 0.012%

    No Known Activations