© 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. 41276
    Prev
    Next
    INDEX
    Explanations

    instances of the word "right" in various contexts

    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
    ita
    -0.17
     rights
    -0.16
    icht
    -0.16
    ات
    -0.15
    IP
    -0.14
    ker
    -0.14
    aab
    -0.14
     réalis
    -0.14
    hyp
    -0.14
    spar
    -0.14
    POSITIVE LOGITS
    eous
    0.41
    -wing
    0.29
    ToLeft
    0.27
    fully
    0.27
    wing
    0.27
    ward
    0.26
    -hand
    0.26
    fulness
    0.23
    zeitig
    0.23
    -ÑĤаки
    0.21
    Activations Density 0.042%

    No Known Activations