© 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. 27-RESID-POST-AA
    11. 113517
    Prev
    Next
    INDEX
    Explanations

    nm

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ดย
    -0.07
     unconscious
    -0.06
     Expansion
    -0.06
    .ReadUInt
    -0.06
    ότητα
    -0.06
     Saul
    -0.06
    р
    -0.06
     리스트
    -0.06
     预
    -0.06
    /sample
    -0.06
    POSITIVE LOGITS
    (AT
    0.08
    .GetOrdinal
    0.06
     Nowadays
    0.06
     comment
    0.06
    _EXTENDED
    0.06
     impactful
    0.06
    _THEME
    0.06
     завдання
    0.06
     gover
    0.06
     dış
    0.05
    Activations Density 0.004%

    No Known Activations