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. 12849
    Prev
    Next
    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on numeric literals that include a decimal point (i.e. floating-point numbers).

    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
     Compensation
    -0.06
    _shadow
    -0.06
    ppard
    -0.06
    userdata
    -0.06
     Dread
    -0.06
     enjoyment
    -0.06
    	templateUrl
    -0.06
    wnd
    -0.06
     logistics
    -0.06
     умень
    -0.06
    POSITIVE LOGITS
     killed
    0.07
     注
    0.07
     Assert
    0.06
     Ads
    0.06
     아닌
    0.06
    _Anim
    0.06
     {//
    0.06
     kidnapped
    0.06
    긴
    0.06
    (BigInteger
    0.06
    Activations Density 0.030%

    No Known Activations