© 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. 15-RESID-POST-AA
    11. 127600
    Prev
    Next
    INDEX
    Explanations

    prison

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    คำ
    -0.07
    jh
    -0.07
     ninja
    -0.07
     간
    -0.07
     vẽ
    -0.06
     convers
    -0.06
    مس
    -0.06
     satur
    -0.06
     Publications
    -0.06
    mtree
    -0.06
    POSITIVE LOGITS
    ibili
    0.06
    -Sep
    0.06
    اورزی
    0.06
    	ASSERT
    0.06
    .ready
    0.06
    .snapshot
    0.06
    циклоп
    0.06
    lid
    0.06
     two
    0.06
     imprisoned
    0.06
    Activations Density 0.044%

    No Known Activations