© 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. 91580
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    source code and programming-related syntax elements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to decimal numeric literals (i.e. floating‐point numbers).

    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
     있다는
    -0.07
    SAMPLE
    -0.06
    inou
    -0.06
     Teach
    -0.06
     locked
    -0.06
     manner
    -0.06
     Governor
    -0.06
     оці
    -0.06
     Иванов
    -0.06
    eness
    -0.06
    POSITIVE LOGITS
    ोषण
    0.06
    _MESH
    0.06
    <div
    0.06
     pulumi
    0.06
    resultado
    0.06
    搞
    0.06
    firstName
    0.06
    adık
    0.06
     команди
    0.06
     ник
    0.06
    Activations Density 0.013%

    No Known Activations