© 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. 41560
    Prev
    Next
    INDEX
    Explanations

    changed

    np_max-act · gemini-2.0-flash

    information about towns and their historical context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects references to renaming events, specifically words in phrases indicating that something “was changed to” a new name.

    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
    بینی
    -0.06
     gems
    -0.06
     бізнес
    -0.06
    ってい
    -0.06
     کش
    -0.06
     вид
    -0.06
    อท
    -0.06
     personalised
    -0.06
    CLUSIVE
    -0.06
    .Slice
    -0.06
    POSITIVE LOGITS
    						↵
    0.07
     corres
    0.07
    �
    0.06
    久久
    0.06
    Registration
    0.06
     Restrictions
    0.06
    ฤษ
    0.06
    240
    0.06
    cccc
    0.06
    /get
    0.06
    Activations Density 0.026%

    No Known Activations