© 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. 42564
    Prev
    Next
    INDEX
    Explanations

    16

    np_max-act · gemini-2.0-flash

    The neuron activates on references to Unicode byte‐order marks and related encoding constants (BOM definitions for UTF formats).

    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
     dicho
    -0.07
    OfType
    -0.06
     yielded
    -0.06
     stud
    -0.06
     certain
    -0.06
    utilities
    -0.06
    [to
    -0.06
    _warnings
    -0.06
    ��
    -0.06
    /render
    -0.06
    POSITIVE LOGITS
    dro
    0.07
     нож
    0.07
    Standard
    0.06
    .move
    0.06
     транспор
    0.06
     Frequ
    0.06
     Milano
    0.06
    java
    0.06
    (Me
    0.06
    大阪
    0.06
    Activations Density 0.001%

    No Known Activations