© 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. 127877
    Prev
    Next
    INDEX
    Explanations

    Negation and critical feedback

    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
     공
    -0.07
    orc
    -0.07
     �
    -0.07
    obic
    -0.07
     validating
    -0.06
    \Persistence
    -0.06
     }↵↵↵
    -0.06
     ล
    -0.06
    kün
    -0.06
    ];//
    -0.06
    POSITIVE LOGITS
     pursuits
    0.06
    gs
    0.06
    	Block
    0.06
    .InvariantCulture
    0.06
     foil
    0.06
     Luo
    0.06
    ’ї
    0.06
     Pot
    0.06
     Nazis
    0.05
    ウォ
    0.05
    Activations Density 0.162%

    No Known Activations