© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91713
    Prev
    Next
    INDEX
    Explanations

    flag

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “flag” (often in code contexts defining or using flag constants, enums, or settings).

    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
     Yun
    -0.08
    enght
    -0.07
     methane
    -0.07
     Allen
    -0.07
     Kur
    -0.07
     tiện
    -0.07
    .Bunifu
    -0.07
    Allen
    -0.07
     zpracování
    -0.07
     purification
    -0.07
    POSITIVE LOGITS
     flag
    0.12
     Flag
    0.12
    flag
    0.11
    Flag
    0.10
     flagged
    0.09
     FLAG
    0.08
     flagship
    0.08
    (FLAGS
    0.08
    .flags
    0.07
    :
    0.07
    Activations Density 0.008%

    No Known Activations