© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92381
    Prev
    Next
    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash

    This neuron responds to byte‐literal escape sequences, especially “\xNN” style hexadecimal escapes in Python byte strings.

    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
     تجربه
    -0.07
    Population
    -0.07
    ropoda
    -0.06
     Regulation
    -0.06
     pods
    -0.06
    Pago
    -0.06
    _ZERO
    -0.06
     rampant
    -0.06
     temple
    -0.06
    Lewis
    -0.06
    POSITIVE LOGITS
     numeral
    0.07
     알려
    0.06
    .stack
    0.06
     frost
    0.06
    วล
    0.06
     BOOL
    0.06
     maka
    0.06
     궁금
    0.06
    >'.
    0.06
    状態
    0.06
    Activations Density 0.004%

    No Known Activations