© 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. 3-RESID-POST-AA
    6. 121530
    Prev
    Next
    INDEX
    Explanations

    ian

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _signals
    -0.07
    (pattern
    -0.06
     Meditation
    -0.06
     Hut
    -0.06
     Singapore
    -0.06
    (chart
    -0.06
     Closed
    -0.06
     strikes
    -0.06
    Singapore
    -0.06
     Bilim
    -0.06
    POSITIVE LOGITS
     avi
    0.08
     Evan
    0.07
    모
    0.07
    atical
    0.07
    astic
    0.07
     rib
    0.07
    ιαν
    0.06
     erotique
    0.06
     amigo
    0.06
     acquitted
    0.06
    Activations Density 0.003%

    No Known Activations