© 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. 125134
    Prev
    Next
    INDEX
    Explanations

    Conversational filler

    np_max-act · gemini-2.0-flash

    The neuron fires on short exclamatory interjections (e.g. “Aw,” “Wow,” “Oh,”) marking moments of surprise or appreciation.

    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
     понять
    -0.07
     cycl
    -0.07
     finder
    -0.06
    prestashop
    -0.06
    Feels
    -0.06
    스템
    -0.06
     شدن
    -0.06
     compt
    -0.06
    fstream
    -0.06
     blockSize
    -0.06
    POSITIVE LOGITS
    しく
    0.06
    ija
    0.06
     reminiscent
    0.06
    razil
    0.06
     minor
    0.06
     (_,
    0.06
     jealous
    0.06
     correspond
    0.06
     yarat
    0.06
     raised
    0.05
    Activations Density 0.032%

    No Known Activations