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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27-RESID-POST-AA
    6. 101811
    Prev
    Next
    INDEX
    Explanations

    say "promoter"

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Violation
    -0.07
     biome
    -0.06
    Tue
    -0.06
    	req
    -0.06
     instrument
    -0.06
    geme
    -0.06
     appropriately
    -0.06
     عدم
    -0.06
    _load
    -0.06
    (...)
    -0.06
    POSITIVE LOGITS
    omanip
    0.07
    543
    0.06
     Tenant
    0.06
     Quaternion
    0.06
     creditor
    0.06
    \Storage
    0.06
    Months
    0.06
     foundational
    0.06
    ист
    0.06
    (helper
    0.06
    Activations Density 0.026%

    No Known Activations