© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121205
    Prev
    Next
    INDEX
    Explanations

    ugo

    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
     array
    -0.07
    Chocolate
    -0.07
     Filtering
    -0.06
    Fixture
    -0.06
     Chocolate
    -0.06
    alties
    -0.06
    thinking
    -0.06
    Sets
    -0.06
    CAP
    -0.06
    uyệ
    -0.06
    POSITIVE LOGITS
    isNaN
    0.14
     Exodus
    0.11
     Hugo
    0.11
     isNaN
    0.10
     Eph
    0.09
    .sleep
    0.09
     sprintf
    0.08
    shima
    0.08
     snprintf
    0.08
     strokeLine
    0.07
    Activations Density 0.004%

    No Known Activations