© 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. 55822
    Prev
    Next
    INDEX
    Explanations

    copies, originals

    np_max-act · gemini-2.0-flash

    legal documents related to court cases and procedures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of required document counts—especially phrases specifying originals and copies.

    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
     unicorn
    -0.06
    ading
    -0.06
     Mis
    -0.06
    林
    -0.06
     Bin
    -0.06
    ил
    -0.06
    eld
    -0.06
     حس
    -0.06
    yas
    -0.06
    Systems
    -0.06
    POSITIVE LOGITS
    /controllers
    0.08
     "?"
    0.07
     pac
    0.07
    indexPath
    0.07
     Acting
    0.07
    +F
    0.06
     unveiling
    0.06
    بات
    0.06
     jspb
    0.06
    Prediction
    0.06
    Activations Density 0.005%

    No Known Activations