© 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 EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 84348
    Prev
    Next
    INDEX
    Explanations

    traditional

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encompass
    -0.08
     chip
    -0.07
     mots
    -0.07
     snippet
    -0.07
     knob
    -0.07
    헤
    -0.06
     наступ
    -0.06
     tweaking
    -0.06
     Palmer
    -0.06
    chemical
    -0.06
    POSITIVE LOGITS
     traditional
    0.09
    	default
    0.07
     tradition
    0.07
    тим
    0.07
     POSIX
    0.07
     bacheca
    0.07
     отд
    0.07
     федера
    0.07
    150
    0.07
    oton
    0.07
    Activations Density 0.014%

    No Known Activations