© 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. 9190
    Prev
    Next
    INDEX
    Explanations

    themes of mentorship and personal identity

    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
    .TXT
    -0.15
    ocaly
    -0.14
    Enumeration
    -0.14
    engkap
    -0.14
    åĵ¡
    -0.13
    ozor
    -0.13
    òng
    -0.13
    inker
    -0.13
    åŁĭ
    -0.13
    opak
    -0.13
    POSITIVE LOGITS
     mentor
    0.58
     mentors
    0.49
     teacher
    0.46
    mentor
    0.45
     Mentor
    0.45
     instructor
    0.45
     instructors
    0.43
     tutor
    0.43
     coach
    0.43
     mentoring
    0.42
    Activations Density 0.033%

    No Known Activations