© 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. 11-RESID-POST-AA
    11. 25851
    Prev
    Next
    INDEX
    Explanations

    Russian meddling

    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
     provincial
    -0.07
    aptop
    -0.06
    _stderr
    -0.06
     thi
    -0.06
    enance
    -0.06
    saving
    -0.06
    iosa
    -0.06
    hid
    -0.05
    ورت
    -0.05
    єю
    -0.05
    POSITIVE LOGITS
     pts
    0.07
     stretched
    0.06
    _callable
    0.06
    .Master
    0.06
    	read
    0.06
     üzere
    0.06
     kra
    0.06
    /**
↵
    0.06
    fallback
    0.06
     lim
    0.06
    Activations Density 0.007%

    No Known Activations