© 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. 23-RESID-POST-AA
    6. 95920
    Prev
    Next
    INDEX
    Explanations

    %

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _instr
    -0.08
    -negative
    -0.07
    387
    -0.06
    Cam
    -0.06
    ி
    -0.06
     weapons
    -0.06
     Foster
    -0.06
     Jew
    -0.06
    (filePath
    -0.06
     x
    -0.06
    POSITIVE LOGITS
    有什么
    0.07
     خویش
    0.07
     рост
    0.07
    اکم
    0.07
     أنها
    0.07
    .Weight
    0.06
    ={↵
    0.06
    کز
    0.06
     حداقل
    0.06
     polled
    0.06
    Activations Density 0.001%

    No Known Activations