© 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. 29989
    Prev
    Next
    INDEX
    Explanations

    formal/technical documents

    np_max-act · gemini-2.0-flash

    This neuron responds to numerical tokens and digit sequences (e.g. “2,” “III,” “10,” version numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to numbers and numeric details such as years, quantities, model/version identifiers, and measurements.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    lood
    -0.07
    Fort
    -0.06
    ถ
    -0.06
    	LEFT
    -0.06
     zmq
    -0.06
    395
    -0.06
    �
    -0.06
    お
    -0.06
     kles
    -0.06
     Armour
    -0.06
    POSITIVE LOGITS
     hasn
    0.07
     According
    0.07
     absolute
    0.07
    ักร
    0.07
     ballistic
    0.06
    .","
    0.06
    .
    0.06
    .Me
    0.06
    +"/"+
    0.06
    beiter
    0.06
    Activations Density 3.912%

    No Known Activations