© 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. 13033
    Prev
    Next
    INDEX
    Explanations

    naval history

    np_max-act · gemini-2.0-flash

    The neuron activates on the names (or parts of the names) of ships and other naval vessels.

    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
     받아
    -0.06
     deine
    -0.06
     homosex
    -0.06
     आत
    -0.06
     entrar
    -0.06
    GEN
    -0.06
    ﻨ
    -0.06
    ант
    -0.06
    mul
    -0.06
     перепис
    -0.06
    POSITIVE LOGITS
    の
    0.06
     fastball
    0.06
     Load
    0.06
    United
    0.06
    些
    0.06
     extras
    0.06
     založ
    0.06
     bef
    0.06
    umi
    0.06
     cupid
    0.06
    Activations Density 0.007%

    No Known Activations