© 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. 126176
    Prev
    Next
    INDEX
    Explanations

    tree algorithms

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (digits or multi‐digit numbers) in code.

    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
     Gotham
    -0.06
    _CLICK
    -0.06
     �
    -0.06
    ################################################
    -0.06
    cole
    -0.06
    Browsable
    -0.06
    _staff
    -0.06
    _publish
    -0.06
     Бер
    -0.06
     Phones
    -0.06
    POSITIVE LOGITS
     dijital
    0.07
    ažd
    0.07
    .usage
    0.06
     Tipo
    0.06
     �
    0.06
     Funding
    0.06
     znamená
    0.06
     THEY
    0.06
     v
    0.06
     council
    0.06
    Activations Density 0.004%

    No Known Activations