© 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. 126622
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes

    np_max-act · gemini-2.0-flash

    This neuron detects temporal transition words—especially “before” (and by extension “after”) indicating a shift in life stages, notably before parenthood.

    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
    155
    -0.07
    setOnClickListener
    -0.07
    -version
    -0.07
     верх
    -0.07
     выб
    -0.06
     biscuits
    -0.06
     ใน
    -0.06
     zk
    -0.06
    unique
    -0.06
     DAR
    -0.06
    POSITIVE LOGITS
    (active
    0.07
     defective
    0.07
     $($
    0.06
     aeros
    0.06
    Specifier
    0.06
    (""
    0.06
    (push
    0.06
    dera
    0.06
     settlements
    0.06
    .alibaba
    0.06
    Activations Density 0.039%

    No Known Activations