Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90546
    Prev
    Next
    INDEX
    Explanations

    convert

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of converting or conversion—i.e. the verb “convert” (and its inflected/gerund forms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    Python code examples for converting data types, specifically focusing on transforming numpy arrays to tuples.

    oai_token-act-pair · gpt-4o-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
     Job
    -0.07
     Drama
    -0.07
     reproduce
    -0.07
     fart
    -0.06
    ча
    -0.06
    Emergency
    -0.06
     Route
    -0.06
    recipe
    -0.06
     BMW
    -0.06
     wards
    -0.06
    POSITIVE LOGITS
    :int
    0.08
    qrst
    0.07
    :ss
    0.07
     NSW
    0.07
    /↵↵↵
    0.07
     haunting
    0.06
    (scroll
    0.06
    OutOfRange
    0.06
     jdbcTemplate
    0.06
     Вели
    0.06
    Activations Density 0.015%

    No Known Activations