© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28956
    Prev
    Next
    INDEX
    Explanations

    before

    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
     traced
    -0.07
     Lynch
    -0.07
     shaped
    -0.06
    /ca
    -0.06
    	answer
    -0.06
     Vers
    -0.06
    	mp
    -0.06
     přeb
    -0.06
     Dob
    -0.06
    navigationBar
    -0.06
    POSITIVE LOGITS
     plung
    0.06
    scribe
    0.06
     preceding
    0.06
     atual
    0.06
     Debian
    0.06
     условиях
    0.06
     무
    0.06
     своего
    0.06
     laut
    0.06
    ится
    0.06
    Activations Density 0.013%

    No Known Activations