© 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. 29649
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate transition or movement away from a situation

    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
    mts
    -0.16
    à¸Īาà¸ģà¸ģาร
    -0.16
    istra
    -0.15
    aca
    -0.15
     Normalize
    -0.15
    ead
    -0.14
    ibs
    -0.14
     awake
    -0.14
    aur
    -0.14
    unei
    -0.14
    POSITIVE LOGITS
     somewhere
    0.29
     to
    0.28
     elsewhere
    0.21
     into
    0.20
     again
    0.19
     disappear
    0.19
     never
    0.17
     towards
    0.17
     Never
    0.17
     disappearing
    0.17
    Activations Density 0.022%

    No Known Activations