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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58687
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on the little decimal confidence-or weight-style numbers (e.g. “0.2366943359375”) used in the model’s explanations.

    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
     opět
    -0.07
     bats
    -0.07
    	us
    -0.06
     endorsed
    -0.06
    -Americans
    -0.06
    Speaking
    -0.06
    мага
    -0.06
    _strings
    -0.06
     appName
    -0.06
     nozzle
    -0.06
    POSITIVE LOGITS
     Minnesota
    0.08
    (SQLException
    0.07
     policing
    0.07
     ole
    0.07
    PING
    0.07
     Jeep
    0.07
     Renewable
    0.06
    _visited
    0.06
     Fucking
    0.06
    Minnesota
    0.06
    Activations Density 0.012%

    No Known Activations