Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104368
    Prev
    Next
    INDEX
    Explanations

    software updates

    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_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
     calibration
    -0.06
     Water
    -0.06
    agonal
    -0.06
     params
    -0.06
    Targets
    -0.05
    แนะนำ
    -0.05
     Raj
    -0.05
     mar
    -0.05
    	default
    -0.05
    roll
    -0.05
    POSITIVE LOGITS
     реє
    0.07
     cyn
    0.07
     پست
    0.06
     Benn
    0.06
     otur
    0.06
     okum
    0.06
     çarp
    0.06
    Cli
    0.06
    Organization
    0.06
     společ
    0.06
    Activations Density 0.021%

    No Known Activations