© 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
    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. 6340
    Prev
    Next
    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash

    This neuron spots the capitalized judge names (e.g. judges listed after “Before”) in the opinion header.

    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
    (Player
    -0.07
    Pool
    -0.07
     Con
    -0.07
     decoder
    -0.07
    '↵↵↵
    -0.06
    Add
    -0.06
    anco
    -0.06
    sam
    -0.06
    _play
    -0.06
    auf
    -0.06
    POSITIVE LOGITS
     dveře
    0.06
    _budget
    0.06
    �
    0.06
     fanc
    0.06
    否
    0.06
    .',↵
    0.06
     měsí
    0.06
    .groupControl
    0.06
     sedm
    0.06
     Tacoma
    0.06
    Activations Density 0.006%

    No Known Activations