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

    Neuronpedia

    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. 127149
    Prev
    Next
    INDEX
    Explanations

    temporal/conditional context

    np_max-act · gemini-2.0-flash

    The neuron detects patent‐style boilerplate qualifiers and discourse markers (e.g. “in general,” “particularly,” “more specifically”) that introduce or frame the invention.

    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
     Orr
    -0.06
     Verification
    -0.06
     numel
    -0.06
     pretending
    -0.06
     LEGO
    -0.06
    Inicial
    -0.06
     personalized
    -0.06
    If
    -0.06
     Ding
    -0.06
     IPP
    -0.06
    POSITIVE LOGITS
    0.07
     hòa
    0.06
    izzie
    0.06
    0.06
    setType
    0.06
     terra
    0.06
    ации
    0.06
    _COMPARE
    0.06
    rides
    0.06
    /on
    0.06
    Activations Density 0.022%

    No Known Activations