© 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. 41479
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron detects isolated uppercase-letter tokens at the start of dialogue lines, i.e. speaker‐name initials in formatted conversations.

    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
     context
    -0.07
    技术
    -0.06
    ickou
    -0.06
     localhost
    -0.06
    ační
    -0.06
     Looking
    -0.06
    ).__
    -0.06
     gode
    -0.06
    abı
    -0.06
     services
    -0.06
    POSITIVE LOGITS
    ="$(
    0.06
    lj
    0.06
    fade
    0.06
    وتی
    0.06
    alous
    0.06
    gran
    0.06
     logarith
    0.06
    Regular
    0.06
     hük
    0.06
     �
    0.06
    Activations Density 0.156%

    No Known Activations