© 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. 55991
    Prev
    Next
    INDEX
    Explanations

    education and schools

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of a person’s education, especially "educated at" followed by a school or college 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
     zusammen
    -0.07
    부터
    -0.06
     одной
    -0.06
    분
    -0.06
    Syn
    -0.06
    Gün
    -0.06
     влаж
    -0.06
     risking
    -0.06
     kilomet
    -0.06
     towel
    -0.06
    POSITIVE LOGITS
    _hw
    0.07
    ционных
    0.06
     origins
    0.06
    Configure
    0.06
    oyal
    0.06
    ErrorException
    0.06
    _prefix
    0.06
     edeb
    0.06
     naive
    0.06
     cellForRowAt
    0.06
    Activations Density 0.005%

    No Known Activations