© 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. 23-RESID-POST-AA
    6. 95879
    Prev
    Next
    INDEX
    Explanations

    ->

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     جمهور
    -0.07
     unanimous
    -0.06
     −
    -0.06
     trồng
    -0.06
    ("{}
    -0.06
     momentarily
    -0.06
     мод
    -0.06
     {-
    -0.06
    Assembly
    -0.06
     bryster
    -0.06
    POSITIVE LOGITS
    hammer
    0.07
    tero
    0.07
    *this
    0.07
    lane
    0.07
     υπάρχ
    0.06
    tright
    0.06
     fantastic
    0.06
     marches
    0.06
    ices
    0.06
    nat
    0.06
    Activations Density 0.003%

    No Known Activations