© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 42356
    Prev
    Next
    INDEX
    Explanations

    neuraminidase/influenza research

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orption
    -0.07
    ohan
    -0.07
    ('</
    -0.06
     성
    -0.06
     جهان
    -0.06
    iciar
    -0.06
     Geç
    -0.06
    (":
    -0.06
     honour
    -0.06
     polarization
    -0.06
    POSITIVE LOGITS
    md
    0.08
     Prior
    0.07
    ยนต
    0.06
    -dd
    0.06
    	tab
    0.06
    sender
    0.06
    оличество
    0.06
     mandates
    0.06
    BD
    0.06
    .GetHashCode
    0.06
    Activations Density 0.001%

    No Known Activations