© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 90701
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects passive‐voice or method‐describing constructions marked by past‐participle verbs (e.g. induced, controlled, driven, promoted) often paired with the preposition “by.”

    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
     videot
    -0.07
     رفته
    -0.07
    UpdatedAt
    -0.07
    ínu
    -0.06
     леж
    -0.06
     Shelter
    -0.06
    打开
    -0.06
     provisioning
    -0.06
    证
    -0.06
    _fecha
    -0.06
    POSITIVE LOGITS
     DataContext
    0.07
    _HAS
    0.07
    ål
    0.07
    fait
    0.06
    _PRIVATE
    0.06
     eternity
    0.06
    さんは
    0.06
    	pt
    0.06
    184
    0.06
     fertil
    0.06
    Activations Density 0.059%

    No Known Activations