© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57673
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    The neuron never activates on any of the input tokens, i.e. it appears to be a “dead” neuron that does not detect any feature.

    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
     room
    -0.08
     Shield
    -0.07
     Room
    -0.07
     rooms
    -0.06
     akci
    -0.06
     RR
    -0.06
     NA
    -0.06
    iy
    -0.06
    DEC
    -0.06
     disks
    -0.06
    POSITIVE LOGITS
     पढ
    0.07
     subdir
    0.07
     Ivanka
    0.07
    咨
    0.07
    ़ें
    0.06
     Refresh
    0.06
     الى
    0.06
     fruity
    0.06
    _levels
    0.06
    (UUID
    0.06
    Activations Density 0.060%

    No Known Activations