© 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. 55404
    Prev
    Next
    INDEX
    Explanations

    party

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect mentions of the legal term “party,” especially in procedural contexts (e.g. “a party may file”).

    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
    DEL
    -0.06
    Montserrat
    -0.06
    iens
    -0.06
     quella
    -0.06
     ApiController
    -0.06
    438
    -0.06
     explic
    -0.06
    /al
    -0.06
     rien
    -0.05
     Note
    -0.05
    POSITIVE LOGITS
    ى
    0.07
    Round
    0.07
     nivel
    0.07
    party
    0.07
     party
    0.07
    mv
    0.06
     leaderboard
    0.06
    roducing
    0.06
     CHANGE
    0.06
    ーバ
    0.06
    Activations Density 0.001%

    No Known Activations