© 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. 123260
    Prev
    Next
    INDEX
    Explanations

    32

    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
     Av
    -0.09
    dots
    -0.07
     Robbie
    -0.07
    borah
    -0.07
     Hort
    -0.07
     aph
    -0.06
     Joseph
    -0.06
    ヴ
    -0.06
    っている
    -0.06
     lässt
    -0.06
    POSITIVE LOGITS
    32
    0.35
    032
    0.15
    64
    0.10
    320
    0.08
    CALL
    0.08
     khi
    0.07
    321
    0.07
    128
    0.07
    34
    0.07
    ۱۲
    0.07
    Activations Density 0.014%

    No Known Activations