© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41336
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    programming constructs and code-related structures, particularly in the context of software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on Go error‐handling patterns, specifically when an `err` variable is compared to `nil` (i.e. `if err != nil { … }`).

    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
    ีฟ
    -0.07
    ')),
    -0.06
     Kum
    -0.06
    _CONFIG
    -0.06
    étique
    -0.06
    �
    -0.06
    	if
    -0.06
    EMPLATE
    -0.06
    ;p
    -0.06
    <!--[
    -0.06
    POSITIVE LOGITS
    Franc
    0.08
    INAL
    0.07
     intensely
    0.07
    Cannot
    0.06
    occo
    0.06
     Failed
    0.06
    cannot
    0.06
    luž
    0.06
     количе
    0.06
     could
    0.06
    Activations Density 0.003%

    No Known Activations