© 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. 15655
    Prev
    Next
    INDEX
    Explanations

    names of prominent individuals or their initials in a specific context

    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
     otherwise
    -0.16
    DeltaTime
    -0.15
    Č↵
    -0.14
    èĩ£
    -0.14
     subject
    -0.14
    REC
    -0.14
    hangi
    -0.13
    irty
    -0.13
    ThanOrEqualTo
    -0.13
    _pi
    -0.13
    POSITIVE LOGITS
    ']!='
    0.16
    _er
    0.15
    iid
    0.15
     ER
    0.14
    estro
    0.14
    .fn
    0.14
    _e
    0.13
    istes
    0.13
    Fold
    0.13
    egin
    0.13
    Activations Density 0.016%

    No Known Activations