© 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. 23-RESID-POST-AA
    6. 12294
    Prev
    Next
    INDEX
    Explanations

    "get the idea"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     고
    -0.07
    ΑΓ
    -0.07
    Unsafe
    -0.06
    rites
    -0.06
     Infer
    -0.06
    yards
    -0.06
    _ent
    -0.06
     �
    -0.06
    enguins
    -0.05
    )initWith
    -0.05
    POSITIVE LOGITS
     갖
    0.06
    орту
    0.06
     लगत
    0.06
    ')==
    0.06
     callbacks
    0.06
     inserts
    0.06
    ΟΥΣ
    0.06
     forfeiture
    0.06
     것
    0.06
    شان
    0.06
    Activations Density 0.035%

    No Known Activations