© 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. 43316
    Prev
    Next
    INDEX
    Explanations

    President

    np_max-act · gemini-2.0-flash

    This neuron detects the occurrence of the title “President” 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
    underline
    -0.07
     Alam
    -0.07
     folk
    -0.07
     collar
    -0.07
    وك
    -0.07
     Lay
    -0.06
     cooler
    -0.06
     alley
    -0.06
     orn
    -0.06
     how
    -0.06
    POSITIVE LOGITS
     President
    0.15
    President
    0.15
     president
    0.13
    -President
    0.11
     Presidents
    0.10
     Presidential
    0.10
     رئيس
    0.10
     presidency
    0.10
    -president
    0.09
     presidential
    0.09
    Activations Density 0.025%

    No Known Activations