© 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. 30045
    Prev
    Next
    INDEX
    Explanations

    lists or enumerations

    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
    _TEX
    -0.07
    cilik
    -0.06
    .pa
    -0.06
     evolved
    -0.06
     conservative
    -0.06
    ployment
    -0.06
    118
    -0.06
    DOMNode
    -0.06
     streaming
    -0.06
    ética
    -0.06
    POSITIVE LOGITS
    aying
    0.06
     Jewish
    0.06
    _assign
    0.06
     mức
    0.06
    ротив
    0.06
     mirrored
    0.06
    шие
    0.06
    ْم
    0.05
     สามารถ
    0.05
    ocomplete
    0.05
    Activations Density 0.331%

    No Known Activations