© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123699
    Prev
    Next
    INDEX
    Explanations

    egregious

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     philosophers
    -0.06
    epend
    -0.06
     mighty
    -0.06
    不知道
    -0.06
    (_.
    -0.06
     đổi
    -0.06
     philosopher
    -0.06
    573
    -0.06
     diferente
    -0.06
    -0.06
    POSITIVE LOGITS
     egregious
    0.14
     blatant
    0.10
    idious
    0.09
     blatantly
    0.09
     prudent
    0.09
    icious
    0.09
     egreg
    0.09
     lingering
    0.08
     innoc
    0.08
    andest
    0.08
    Activations Density 0.010%

    No Known Activations