© 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. 11-RESID-POST-AA
    11. 124890
    Prev
    Next
    INDEX
    Explanations

    IB

    np_max-act · gemini-2.0-flash

    This neuron fires on the base-64–encoded payload inside PEM blocks (e.g. the long MI…/E… strings in “BEGIN … KEY” or “BEGIN CERTIFICATE” sections).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itud
    -0.07
    ่ย
    -0.07
    ]";↵
    -0.06
    φυ
    -0.06
    -clear
    -0.06
     dipl
    -0.06
    .measure
    -0.06
    ادگی
    -0.06
    -0.06
     장
    -0.06
    POSITIVE LOGITS
     شمالی
    0.07
    .ads
    0.07
     Website
    0.07
     unittest
    0.07
     Replay
    0.06
     dame
    0.06
     reviewing
    0.06
    ']."</
    0.06
     český
    0.06
     massive
    0.06
    Activations Density 0.001%
    No Known Activations