© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21951
    Prev
    Next
    INDEX
    Explanations

    say Win

    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
    _strcmp
    -0.07
    ویل
    -0.07
     trường
    -0.07
    _REQUIRED
    -0.07
     magnet
    -0.06
    ----------
    -0.06
    (prop
    -0.06
    ΡΙ
    -0.06
    _DIALOG
    -0.06
     Country
    -0.06
    POSITIVE LOGITS
     kapsam
    0.06
    тый
    0.06
    	pstmt
    0.06
     풍
    0.06
    삼
    0.06
    _FORCE
    0.06
     Pound
    0.06
    čné
    0.06
    �
    0.06
     subplot
    0.06
    Activations Density 0.004%

    No Known Activations