© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 80386
    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extracting
    -0.07
    	S
    -0.07
     Sche
    -0.07
    CAR
    -0.07
    	description
    -0.06
    small
    -0.06
    027
    -0.06
     종
    -0.06
    plies
    -0.06
    }\\
    -0.06
    POSITIVE LOGITS
     vững
    0.06
     witches
    0.06
    部门
    0.06
    .lab
    0.06
    ウト
    0.06
     topp
    0.06
     а
    0.06
     rhs
    0.06
    λου
    0.06
    ="<?=
    0.06
    Activations Density 0.039%

    No Known Activations