© 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. 6850
    Prev
    Next
    INDEX
    Explanations

    peroxisome receptors

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “peroxisome proliferator‐activated receptor” (PPAR) family or closely related receptor terminology.

    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
    Manage
    -0.07
    �
    -0.07
    _ROUT
    -0.07
     vw
    -0.07
    https
    -0.07
     جديدة
    -0.07
    омет
    -0.06
    AKER
    -0.06
    XR
    -0.06
    	flash
    -0.06
    POSITIVE LOGITS
     آمریک
    0.06
    erif
    0.06
    听到
    0.06
    _noise
    0.06
    TypeID
    0.06
     penetrated
    0.06
     intermittent
    0.06
    entions
    0.06
     unfairly
    0.06
     httpClient
    0.06
    Activations Density 0.442%

    No Known Activations