© 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. 126249
    Prev
    Next
    INDEX
    Explanations

    script dialogues

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to fragments of proper names (especially character names) split across tokens.

    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
    xd
    -0.07
    httpClient
    -0.06
     studios
    -0.06
    ,next
    -0.06
    Sentence
    -0.06
    nick
    -0.06
    beiten
    -0.06
     guts
    -0.06
     waiver
    -0.06
     artistic
    -0.05
    POSITIVE LOGITS
    	scanf
    0.07
    .unshift
    0.07
    ateria
    0.06
    (uuid
    0.06
    EF
    0.06
     можна
    0.06
     feliz
    0.06
    Mapped
    0.06
     Lockheed
    0.06
    ельзя
    0.06
    Activations Density 0.018%

    No Known Activations