© 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. 127822
    Prev
    Next
    INDEX
    Explanations

    easy simple

    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
     FAILED
    -0.07
    QObject
    -0.07
     möchte
    -0.06
    ibre
    -0.06
    模式
    -0.06
     partnership
    -0.06
    케
    -0.06
    leased
    -0.06
    _stop
    -0.06
     Wet
    -0.06
    POSITIVE LOGITS
    >.</
    0.07
     Müller
    0.06
    ?>:</
    0.06
    iles
    0.06
    Bins
    0.06
     Charlottesville
    0.06
    κει
    0.06
    	afx
    0.06
     jedn
    0.06
     fos
    0.06
    Activations Density 0.029%

    No Known Activations