© 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. 7-RESID-POST-AA
    11. 48932
    Prev
    Next
    INDEX
    Explanations

    lawsuits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cette
    -0.07
    」的
    -0.07
    慧
    -0.07
     Kuwait
    -0.07
    화를
    -0.06
    .enemy
    -0.06
    	in
    -0.06
    /{{$
    -0.06
    .dgv
    -0.06
    .Unique
    -0.06
    POSITIVE LOGITS
     warriors
    0.07
    เพลง
    0.07
    AdminController
    0.06
    ़्
    0.06
    AlmostEqual
    0.06
     mortgage
    0.06
     occurs
    0.06
     discharge
    0.06
     ques
    0.06
    Whitespace
    0.06
    Activations Density 0.020%

    No Known Activations