© 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. 40981
    Prev
    Next
    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash

    The neuron looks for the “No. <digits>” docket‐number line in legal case citations (i.e. the case number following “No.”).

    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
    Poll
    -0.07
    /devices
    -0.07
     Copp
    -0.07
    Question
    -0.06
    SignUp
    -0.06
    ops
    -0.06
     러
    -0.06
     Hed
    -0.06
    pler
    -0.06
    dealloc
    -0.06
    POSITIVE LOGITS
    utely
    0.06
     lows
    0.06
     behaving
    0.06
    ých
    0.06
    κα
    0.06
    _TBL
    0.06
    щая
    0.06
     máte
    0.06
     dread
    0.06
     كبير
    0.05
    Activations Density 0.010%

    No Known Activations