© 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. 15-RESID-POST-AA
    11. 27629
    Prev
    Next
    INDEX
    Explanations

    |

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reward
    -0.06
    Sou
    -0.06
     enh
    -0.06
     mars
    -0.06
    сько
    -0.06
     تبلی
    -0.06
    hani
    -0.06
    EF
    -0.06
    Mapped
    -0.06
     Midi
    -0.05
    POSITIVE LOGITS
    ification
    0.07
    -important
    0.06
     GREAT
    0.06
    (Node
    0.06
     refrigerator
    0.06
     misuse
    0.06
    ekyll
    0.06
     willingness
    0.06
     principio
    0.06
     Dungeon
    0.06
    Activations Density 0.000%

    No Known Activations