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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2606
    Prev
    Next
    INDEX
    Explanations

    instances of the word "or" and its variations indicating uncertainty or alternatives

    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
    empo
    -0.18
    plx
    -0.17
    eph
    -0.15
    ego
    -0.15
    enu
    -0.15
    ency
    -0.15
    unami
    -0.15
    kola
    -0.14
    opup
    -0.14
    Forge
    -0.14
    POSITIVE LOGITS
     not
    0.46
    not
    0.36
     Not
    0.32
    Not
    0.32
     NOT
    0.28
    ifice
    0.27
    ä¸į
    0.26
    _not
    0.26
    phans
    0.25
    -not
    0.25
    Activations Density 0.042%

    No Known Activations