© 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. 92779
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     js
    -0.07
     FixedUpdate
    -0.07
    _AREA
    -0.06
     comment
    -0.06
     подраз
    -0.06
     Download
    -0.06
    987
    -0.06
     ==
    -0.06
     encoder
    -0.06
    ере
    -0.06
    POSITIVE LOGITS
     بالأ
    0.06
    ’aut
    0.06
     trest
    0.06
     gasoline
    0.06
    skému
    0.06
     mistakenly
    0.06
    (Position
    0.06
    **(
    0.06
     sounding
    0.06
    $options
    0.06
    Activations Density 0.045%

    No Known Activations