© 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. 55473
    Prev
    Next
    INDEX
    Explanations

    records

    np_max-act · gemini-2.0-flash

    The neuron activates on record‐label names (e.g. “Warner Records,” “MCA Records,” “Island Records”) in the category metadata.

    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
    acao
    -0.06
     imageName
    -0.06
     گرفته
    -0.06
     sø
    -0.06
    드리
    -0.06
     olduğu
    -0.06
     Wikip
    -0.06
    된다
    -0.06
     franca
    -0.06
    _SENS
    -0.06
    POSITIVE LOGITS
     ряд
    0.08
    _framework
    0.07
     stones
    0.07
     Elasticsearch
    0.06
     vaccinated
    0.06
    ันธ
    0.06
    laws
    0.06
    olutions
    0.06
     Votes
    0.06
    领导
    0.06
    Activations Density 0.006%

    No Known Activations