© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55879
    Prev
    Next
    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash

    This neuron detects the formal “Honorable … Judge Presiding” header lines that name the presiding judge in court opinions.

    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
     fundamentals
    -0.07
     entered
    -0.07
    .assertNotNull
    -0.07
    (branch
    -0.07
     mechanically
    -0.07
     celebrated
    -0.07
     share
    -0.07
     vive
    -0.07
     mechanical
    -0.07
     knives
    -0.07
    POSITIVE LOGITS
    โครงการ
    0.07
    (hw
    0.07
     gerç
    0.07
     Ί
    0.06
    TriState
    0.06
     شه
    0.06
    LIBINT
    0.06
     gigg
    0.06
     viewType
    0.06
     funkci
    0.06
    Activations Density 0.006%

    No Known Activations