© 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. 15-RESID-POST-AA
    6. 13323
    Prev
    Next
    INDEX
    Explanations

    Lists of things

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .д
    -0.07
     UIButton
    -0.07
    _isr
    -0.07
    一页
    -0.06
    ไข
    -0.06
    .ac
    -0.06
    소개
    -0.06
    кий
    -0.06
    +h
    -0.06
     hayvan
    -0.06
    POSITIVE LOGITS
     đương
    0.06
     workspace
    0.06
     pasar
    0.06
     Sokol
    0.06
     chromat
    0.06
     sqr
    0.06
     cooker
    0.06
     retVal
    0.06
    /player
    0.06
     insider
    0.06
    Activations Density 0.064%

    No Known Activations