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. 11-RESID-POST-AA
    6. 118228
    Prev
    Next
    INDEX
    Explanations

    encoded sequences

    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
     objs
    -0.07
    Fault
    -0.06
     Enterprises
    -0.06
    word
    -0.06
    Svc
    -0.06
     Alberto
    -0.06
    spb
    -0.06
    -word
    -0.06
    italic
    -0.06
     Manufacturers
    -0.06
    POSITIVE LOGITS
     dispensaries
    0.07
     divisible
    0.06
     recht
    0.06
     classified
    0.06
     réalis
    0.06
     misdemean
    0.06
    teří
    0.06
     ];↵
    0.06
     Oper
    0.06
     rootView
    0.06
    Activations Density 0.006%

    No Known Activations