© 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. 7-RESID-POST-AA
    11. 94015
    Prev
    Next
    INDEX
    Explanations

    patients

    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
    。それ
    -0.07
    /xml
    -0.07
     REF
    -0.07
     THAN
    -0.07
     TSA
    -0.06
    ATORS
    -0.06
    atic
    -0.06
    uario
    -0.06
     베
    -0.06
    \\\\
    -0.06
    POSITIVE LOGITS
     europé
    0.07
    ])]↵
    0.07
    .isEnabled
    0.06
     inval
    0.06
     meget
    0.06
    >ID
    0.06
    CharArray
    0.06
     Kaplan
    0.06
    達
    0.06
    保
    0.06
    Activations Density 0.021%

    No Known Activations