© 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. 8941
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on lower-case tokens that name infrastructure or service components (e.g. “web,” “site,” “cluster,” “mesosphere”) in configuration or deployment contexts.

    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
    enty
    -0.07
     cảnh
    -0.07
    Adds
    -0.06
     keer
    -0.06
     dung
    -0.06
     กำ
    -0.06
    (handler
    -0.06
    .osgi
    -0.06
    usty
    -0.06
     Ramos
    -0.06
    POSITIVE LOGITS
    يس
    0.06
     профес
    0.06
    .getToken
    0.06
     retard
    0.06
    LLL
    0.06
    	TokenName
    0.06
    بع
    0.06
    °С
    0.06
    uniacid
    0.06
     diminish
    0.06
    Activations Density 0.068%

    No Known Activations