© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44233
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “The,” especially when it appears as the initial word of a sentence or heading.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Easily
    -0.08
     newborn
    -0.08
    	of
    -0.07
     this
    -0.07
     对
    -0.07
    旋
    -0.06
     we
    -0.06
    _INC
    -0.06
     加
    -0.06
    iang
    -0.06
    POSITIVE LOGITS
     The
    0.12
    The
    0.10
    	The
    0.07
    _variable
    0.07
     verdienen
    0.06
     Booker
    0.06
    (token
    0.06
     initWithStyle
    0.06
     CGContext
    0.06
    Tho
    0.06
    Activations Density 0.275%

    No Known Activations