© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 89287
    Prev
    Next
    INDEX
    Explanations

    -fold

    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
    Names
    -0.08
    +y
    -0.07
    ्तन
    -0.07
    .latest
    -0.06
    CHEDULE
    -0.06
    атом
    -0.06
    €€€€
    -0.06
    ιά
    -0.06
    χ
    -0.06
     FirebaseFirestore
    -0.06
    POSITIVE LOGITS
    .variant
    0.07
     istedi
    0.06
     Фор
    0.06
    adx
    0.06
     mutlu
    0.06
     Alan
    0.06
    pix
    0.06
     Iceland
    0.06
     Pump
    0.06
     MSD
    0.06
    Activations Density 0.264%

    No Known Activations