© 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. 3-RESID-POST-AA
    6. 123356
    Prev
    Next
    INDEX
    Explanations

    -described

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$('#
    -0.07
    тя
    -0.07
    RESOURCE
    -0.06
    #,
    -0.06
    ủng
    -0.06
     _,
    -0.06
     strengthening
    -0.06
    oes
    -0.06
    ;"></
    -0.06
     _:
    -0.06
    POSITIVE LOGITS
    -described
    0.19
    =sum
    0.07
    اپ
    0.06
     specialized
    0.06
    idx
    0.06
    	seq
    0.06
    付き
    0.06
    cal
    0.06
    annot
    0.06
    :YES
    0.06
    Activations Density 0.001%

    No Known Activations