© 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. 126060
    Prev
    Next
    INDEX
    Explanations

    happiness and satisfaction

    np_max-act · gemini-2.0-flash

    The neuron fires on abstract moral‐oriented terms and reflections—words like “happiness,” “satisfaction,” “internal,” “growth,” and similar concepts in a moral lesson or philosophical conclusion.

    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
    勒
    -0.07
    унк
    -0.07
    яс
    -0.07
    ียด
    -0.06
    vertising
    -0.06
    ugas
    -0.06
    ('/')↵
    -0.06
    pmat
    -0.06
     вза
    -0.06
    button
    -0.06
    POSITIVE LOGITS
    fx
    0.06
    ret
    0.06
     deadlock
    0.06
    imits
    0.06
     Jets
    0.06
     antennas
    0.06
    ौक
    0.06
    .Real
    0.06
     adore
    0.06
     jets
    0.06
    Activations Density 0.061%

    No Known Activations