© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41569
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron is detecting adjectives that highlight physical attractiveness or appeal (e.g., “attractive”).

    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
     б
    -0.07
     внутрен
    -0.07
    .OPEN
    -0.07
    (sys
    -0.06
    /orders
    -0.06
    .wait
    -0.06
    ейн
    -0.06
    Pie
    -0.06
     flushed
    -0.06
     fav
    -0.06
    POSITIVE LOGITS
     зробити
    0.08
     verificar
    0.06
    iral
    0.06
     danych
    0.06
     cocktails
    0.06
     тебя
    0.06
    мати
    0.06
    ¶
    0.06
    عمل
    0.06
     провести
    0.06
    Activations Density 0.040%

    No Known Activations