© 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. 125161
    Prev
    Next
    INDEX
    Explanations

    Vitamin B12

    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
    -centric
    -0.07
    _CTX
    -0.07
    doi
    -0.07
    élé
    -0.07
    oproject
    -0.06
    jualan
    -0.06
    _page
    -0.06
    BlockSize
    -0.06
    appointed
    -0.06
     Reporter
    -0.06
    POSITIVE LOGITS
    /apache
    0.06
    056
    0.06
    009
    0.06
     profoundly
    0.06
     आक
    0.06
    ملكة
    0.05
     unge
    0.05
     dosp
    0.05
     blitz
    0.05
     caut
    0.05
    Activations Density 0.060%

    No Known Activations