© 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. 32903
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes related to self-referential concepts

    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
    puts
    -0.17
    ungle
    -0.16
    ismus
    -0.16
    .oc
    -0.14
    olume
    -0.14
    exels
    -0.14
    illis
    -0.13
     dre
    -0.13
    ssize
    -0.13
    qi
    -0.13
    POSITIVE LOGITS
    /self
    0.27
     self
    0.23
    ģm
    0.19
    (Self
    0.18
     Self
    0.18
    self
    0.17
    (self
    0.17
     SELF
    0.17
    ,self
    0.16
    лÑĥÑĪ
    0.16
    Activations Density 0.014%

    No Known Activations