© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54159
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of courts or appellate court citations (e.g., “Court of Appeals”).

    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
    (and
    -0.07
    .gca
    -0.06
    College
    -0.06
     intermedi
    -0.06
    يلاد
    -0.06
     marginLeft
    -0.06
    scala
    -0.06
    _SAMPL
    -0.06
    リング
    -0.06
    参照
    -0.06
    POSITIVE LOGITS
     completion
    0.07
    Photo
    0.07
    othy
    0.07
    itty
    0.06
    (logging
    0.06
    ACHI
    0.06
    IGHT
    0.06
     jednodu
    0.06
     ipAddress
    0.06
    	throws
    0.06
    Activations Density 0.003%

    No Known Activations