© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 93736
    Prev
    Next
    INDEX
    Explanations

    (

    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
    HUD
    -0.07
     Podle
    -0.06
     exception
    -0.06
    ingle
    -0.06
    .Localization
    -0.06
     distribute
    -0.06
     phishing
    -0.06
     boutique
    -0.06
    иск
    -0.06
    romě
    -0.06
    POSITIVE LOGITS
    	freopen
    0.08
    �
    0.06
    ----------
↵
    0.06
     contentValues
    0.06
     localObject
    0.06
     Пав
    0.06
     Drake
    0.06
     Benson
    0.06
     пунк
    0.06
    ога
    0.06
    Activations Density 0.018%

    No Known Activations