© 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. 11-RESID-POST-AA
    6. 108787
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to the two‐letter sequence “iv” (i.e. it activates on identifiers or tokens containing “iv”).

    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
    (rec
    -0.06
     attack
    -0.06
     استر
    -0.06
     grenade
    -0.06
    xED
    -0.06
    supply
    -0.06
     intake
    -0.06
    .ObjectMapper
    -0.06
    _key
    -0.06
    _passwd
    -0.06
    POSITIVE LOGITS
    очатку
    0.06
    !'↵
    0.06
    ,"↵
    0.06
    alth
    0.06
    arth
    0.06
    ien
    0.06
     luận
    0.06
    (URL
    0.06
    PositiveButton
    0.05
    bash
    0.05
    Activations Density 0.010%

    No Known Activations