© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110461
    Prev
    Next
    INDEX
    Explanations

    legal statements

    np_max-act · gemini-2.0-flash

    This neuron activates on verbs that attribute statements or reports (e.g. “said,” “stating,” “reported”).

    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
    iors
    -0.06
    อป
    -0.06
     bob
    -0.06
    980
    -0.06
     flagged
    -0.06
    사람
    -0.06
    _lower
    -0.06
     LS
    -0.06
    лав
    -0.05
     Red
    -0.05
    POSITIVE LOGITS
     strerror
    0.07
    먼
    0.07
     parted
    0.07
     verd
    0.07
    BarButton
    0.06
     morb
    0.06
    Produces
    0.06
     craving
    0.06
    $scope
    0.06
     minimized
    0.06
    Activations Density 0.016%

    No Known Activations