© 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. 15-RESID-POST-AA
    6. 128867
    Prev
    Next
    INDEX
    Explanations

    code

    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
    amenti
    -0.08
    .over
    -0.07
    	dest
    -0.07
    _Rect
    -0.07
    rze
    -0.06
    "The
    -0.06
     contempl
    -0.06
    mill
    -0.06
    	parent
    -0.06
    >();
    -0.06
    POSITIVE LOGITS
    ışı
    0.07
     yoktur
    0.07
    listed
    0.07
    条件
    0.07
     Anglo
    0.07
     edm
    0.07
     refusing
    0.06
    APPLICATION
    0.06
     کاربرد
    0.06
    uggestion
    0.06
    Activations Density 0.000%

    No Known Activations