© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43268
    Prev
    Next
    INDEX
    Explanations

    ding

    np_max-act · gemini-2.0-flash

    This neuron detects words or phrases that denote obstacles or obstructions, such as “creative blocks” or “overcrowding.”

    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
    issued
    -0.07
    quets
    -0.07
     Magnum
    -0.07
     disks
    -0.06
     Suite
    -0.06
    -hash
    -0.06
    ingham
    -0.06
    吃
    -0.06
     vra
    -0.06
     whats
    -0.06
    POSITIVE LOGITS
    :'',
    0.08
    Empty
    0.07
     represent
    0.06
     "-"↵
    0.06
     Label
    0.06
    şehir
    0.06
    !).↵↵
    0.06
     �
    0.06
    ionic
    0.06
     dangerous
    0.06
    Activations Density 0.129%

    No Known Activations