© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13587
    Prev
    Next
    INDEX
    Explanations

    Biographical, education texts

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases describing a person’s formal education—degree names, institutions attended, graduation details, and related academic credentials.

    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
    ),"
    -0.07
    Strategy
    -0.06
    ITS
    -0.06
     otevř
    -0.06
    	options
    -0.06
    451
    -0.06
    Thank
    -0.06
     ve
    -0.06
    Numer
    -0.06
     McGu
    -0.06
    POSITIVE LOGITS
    chers
    0.07
    μένες
    0.06
     原
    0.06
     blasted
    0.06
     selfie
    0.06
    如下
    0.06
     upkeep
    0.06
     Usage
    0.06
     lineWidth
    0.06
    ваются
    0.06
    Activations Density 0.027%

    No Known Activations