© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52445
    Prev
    Next
    INDEX
    Explanations

    st

    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
    až
    -0.07
    βέρ
    -0.07
     folded
    -0.06
    where
    -0.06
    ITTER
    -0.06
    ΥΡ
    -0.06
    	X
    -0.06
    `)
    -0.06
    ανα
    -0.06
    ancellable
    -0.06
    POSITIVE LOGITS
    .removeItem
    0.07
    .rnn
    0.06
     increasing
    0.06
     Nd
    0.06
     cbd
    0.06
     exceedingly
    0.06
    :x
    0.06
     Record
    0.06
    ंडल
    0.06
     Issues
    0.06
    Activations Density 0.305%

    No Known Activations