© 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. 101340
    Prev
    Next
    INDEX
    Explanations

    military bases

    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
    Cs
    -0.07
     motivation
    -0.06
     folk
    -0.06
    {}",
    -0.06
     dirent
    -0.06
     one
    -0.06
    Dir
    -0.06
    uhn
    -0.06
     indu
    -0.06
     Navigate
    -0.06
    POSITIVE LOGITS
    profit
    0.08
    _EXPI
    0.07
     mortgage
    0.07
     vorhand
    0.06
    .nb
    0.06
     PGA
    0.06
    Recovered
    0.06
     mojo
    0.06
     Madness
    0.06
    ]string
    0.06
    Activations Density 0.016%

    No Known Activations