© 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. 130320
    Prev
    Next
    INDEX
    Explanations

    Late night talk shows

    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
     melakukan
    -0.07
     sar
    -0.07
    QObject
    -0.07
     cheesy
    -0.07
     reminis
    -0.07
     查
    -0.06
     Dou
    -0.06
     HT
    -0.06
     dou
    -0.06
    .mipmap
    -0.06
    POSITIVE LOGITS
     alors
    0.06
    ential
    0.06
    air
    0.06
    ﾞﾞ
    0.06
     Descriptor
    0.06
    mal
    0.06
    (Parse
    0.06
    NBC
    0.06
    资源
    0.06
     уж
    0.06
    Activations Density 0.020%

    No Known Activations