© 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 EvalsExportsinterp-engineNEWAPI 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. 27-RESID-POST-AA
    11. 18676
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     balloon
    -0.08
    ین
    -0.07
    Offset
    -0.07
    Rights
    -0.07
    WAY
    -0.07
     Triple
    -0.06
     Mercury
    -0.06
    abic
    -0.06
    *T
    -0.06
     triple
    -0.06
    POSITIVE LOGITS
    .dispatch
    0.08
    _FOLLOW
    0.06
     objetivo
    0.06
     đăng
    0.06
     john
    0.06
    Ack
    0.06
    ataires
    0.06
    .ForEach
    0.06
     kiểm
    0.06
     Phill
    0.06
    Activations Density 0.122%

    No Known Activations