© 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. 30098
    Prev
    Next
    INDEX
    Explanations

    say "into"

    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
     Selected
    -0.06
    stored
    -0.06
    ées
    -0.06
    _viewer
    -0.06
    Configs
    -0.06
     콘
    -0.06
    �
    -0.06
    Verified
    -0.06
     hale
    -0.06
     shuts
    -0.06
    POSITIVE LOGITS
    椅
    0.06
     сна
    0.06
    _reduce
    0.06
     JComboBox
    0.06
    LEX
    0.06
    .How
    0.06
     funkc
    0.06
     addslashes
    0.06
     zřejmě
    0.06
    less
    0.06
    Activations Density 0.039%

    No Known Activations