© 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. 55413
    Prev
    Next
    INDEX
    Explanations

    dissent

    np_max-act · gemini-2.0-flash

    The neuron activates on references to a dissenting opinion (e.g. “dissent” or “dissenting”).

    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
    CloseOperation
    -0.07
     Cleaning
    -0.07
    ('[
    -0.06
    xxx
    -0.06
     };↵↵↵
    -0.06
    _LICENSE
    -0.06
     getTitle
    -0.06
    _name
    -0.06
     EnumerableStream
    -0.06
    .cv
    -0.06
    POSITIVE LOGITS
     Breast
    0.08
     Blazers
    0.07
     đào
    0.06
    atham
    0.06
    骨
    0.06
     EL
    0.06
     đảo
    0.06
    /sp
    0.06
     U
    0.06
     pena
    0.06
    Activations Density 0.002%

    No Known Activations