© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56529
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects the formal appellate disposition language at the end of opinions (e.g. “ORDERED that the order is affirmed/reversed” and related decision‐statement phrases).

    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
     moderate
    -0.07
     Psi
    -0.06
    .adjust
    -0.06
    CONTEXT
    -0.06
    드리
    -0.06
    073
    -0.06
     discriminator
    -0.06
    ovie
    -0.06
    avi
    -0.06
    063
    -0.06
    POSITIVE LOGITS
    UILDER
    0.07
    (IService
    0.07
     Καρ
    0.06
    _PROF
    0.06
    $result
    0.06
    _ctrl
    0.06
     warfare
    0.06
     fours
    0.06
    ισε
    0.06
    .swift
    0.06
    Activations Density 0.005%

    No Known Activations