© 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. 12660
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash

    specific steps or processes related to program development and implementation.

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

    The neuron detects mentions of the “target audience,” audience definitions, and related phrasing about who a given plan or proposal is aimed at.

    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
    epam
    -0.07
    inheritDoc
    -0.07
    .IsValid
    -0.06
    Dam
    -0.06
     appar
    -0.06
    Obviously
    -0.06
    Для
    -0.06
    Import
    -0.06
    .invalid
    -0.06
    prev
    -0.06
    POSITIVE LOGITS
     hike
    0.07
     especial
    0.07
     LAN
    0.06
     ",↵
    0.06
     Savaşı
    0.06
     answered
    0.06
    piel
    0.06
     suf
    0.06
    _tabs
    0.06
    psc
    0.06
    Activations Density 0.105%

    No Known Activations