© 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. 766
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on instructional or advisory text that directly addresses the reader (e.g. “you,” “ensure,” “will,” “keep you posted,” etc.), signaling it’s spotting second-person guidance or recommendations.

    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
    انس
    -0.06
    empre
    -0.06
     tus
    -0.06
     STOP
    -0.06
     prioritize
    -0.06
    apture
    -0.06
    OVID
    -0.06
    Though
    -0.06
     hott
    -0.06
     Alaska
    -0.06
    POSITIVE LOGITS
    .setResult
    0.06
    MFLOAT
    0.06
     dedi
    0.06
    _pin
    0.06
     druhé
    0.06
    iasm
    0.06
     Artikel
    0.06
     Reference
    0.06
    	System
    0.05
    ISMATCH
    0.05
    Activations Density 1.620%

    No Known Activations