© 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. 27-RESID-POST-AA
    6. 45502
    Prev
    Next
    INDEX
    Explanations

    say "de" word

    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
     pipeline
    -0.07
    ському
    -0.06
    ��
    -0.06
    Manager
    -0.06
    ============
    -0.06
    =np
    -0.06
     Mouse
    -0.06
    ]),
    -0.06
    _sv
    -0.06
    ]]
    -0.06
    POSITIVE LOGITS
    �
    0.08
    .react
    0.07
    ومی
    0.07
     Balk
    0.07
     blatant
    0.07
     αντι
    0.07
    ालन
    0.07
    .forName
    0.06
     пы
    0.06
     bargaining
    0.06
    Activations Density 0.004%

    No Known Activations