Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 7619
    Prev
    Next
    INDEX
    Explanations

    say "Sie"

    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
     tink
    -0.07
     reservation
    -0.06
     Country
    -0.06
    --↵↵
    -0.06
    ภาษ
    -0.06
     salad
    -0.06
    isp
    -0.06
     tenga
    -0.06
    };
    ↵
    ↵
    -0.06
    :
    -0.06
    POSITIVE LOGITS
     کن
    0.07
    との
    0.06
    ở
    0.06
     '%"
    0.06
    akhstan
    0.06
    oplan
    0.06
    Russian
    0.06
    Alternate
    0.06
    ví
    0.06
     touring
    0.06
    Activations Density 0.010%

    No Known Activations