© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12592
    Prev
    Next
    INDEX
    Explanations

    pattern

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “pattern” (and its variants such as “patterns,” “patterning,” etc.) in the text.

    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
     黄
    -0.06
    022
    -0.06
    og
    -0.06
    science
    -0.06
    tainment
    -0.06
     друг
    -0.06
     Fayette
    -0.06
     Ri
    -0.06
    _logger
    -0.06
    aud
    -0.06
    POSITIVE LOGITS
    Finding
    0.07
    �
    0.06
     Finding
    0.06
     Midi
    0.06
     gereken
    0.06
     Sinn
    0.06
     steht
    0.06
    멘
    0.06
     wanting
    0.06
     guarda
    0.06
    Activations Density 0.007%

    No Known Activations