© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44225
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron spotlights the numeric volume and page elements of legal case citations (e.g. “347 Ill. App. 3d 113”).

    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
    .references
    -0.06
    project
    -0.06
     waitress
    -0.06
    -condition
    -0.06
    TODO
    -0.06
    -target
    -0.06
    _fixture
    -0.06
    İng
    -0.05
     ceramics
    -0.05
    /gen
    -0.05
    POSITIVE LOGITS
     deliberately
    0.07
    μαι
    0.07
     largely
    0.07
    目标
    0.06
    inge
    0.06
    rescia
    0.06
     شمال
    0.06
     there
    0.06
    	define
    0.06
     WaitFor
    0.06
    Activations Density 0.003%

    No Known Activations