© 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. 89678
    Prev
    Next
    INDEX
    Explanations

    cars and roads

    np_max-act · gemini-2.0-flash

    The neuron activates most strongly on words referring to driving or being on the road.

    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
     pistols
    -0.06
     presidential
    -0.06
     jav
    -0.06
     Redux
    -0.06
    melon
    -0.06
    Blocking
    -0.06
     Presidential
    -0.06
    Π
    -0.06
    άλ
    -0.06
     boxing
    -0.06
    POSITIVE LOGITS
    ğiniz
    0.07
    خذ
    0.07
     đường
    0.07
     Phương
    0.06
     autonomous
    0.06
    _coordinate
    0.06
     resposta
    0.06
    kün
    0.06
    .Movie
    0.06
    χία
    0.06
    Activations Density 0.063%

    No Known Activations