© 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. 113245
    Prev
    Next
    INDEX
    Explanations

    upp

    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
     feedback
    -0.07
    对象
    -0.06
     learners
    -0.06
     nhờ
    -0.06
     ante
    -0.06
    ("/
    -0.06
     schema
    -0.06
    Liverpool
    -0.06
     squares
    -0.06
    ‌م
    -0.06
    POSITIVE LOGITS
     inhib
    0.06
    ايات
    0.06
     TIMESTAMP
    0.06
    нивер
    0.06
    .pos
    0.06
     bombard
    0.06
     Battalion
    0.06
    atori
    0.06
    Dragon
    0.06
     resets
    0.06
    Activations Density 0.005%

    No Known Activations