© 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. 109479
    Prev
    Next
    INDEX
    Explanations

    Late fees

    np_max-act · gemini-2.0-flash

    phrases related to payment and financial obligations.

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

    This neuron activates on tokens related to financial penalties and charges (e.g., “late,” “fees,” “interest,” “penalties,” “due”).

    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
     auf
    -0.07
    -М
    -0.06
     ;-
    -0.06
    HEAD
    -0.06
     kont
    -0.06
     sotto
    -0.06
    izarre
    -0.06
     Maya
    -0.06
     realizar
    -0.06
    ``,
    -0.06
    POSITIVE LOGITS
     видно
    0.07
    _WINDOWS
    0.06
     غر
    0.06
    wagon
    0.06
    enet
    0.06
    008
    0.06
    �
    0.06
     Helper
    0.06
    eed
    0.06
    icable
    0.06
    Activations Density 0.007%

    No Known Activations