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. 20535
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Hwy
    -0.07
     cottage
    -0.07
    Snippet
    -0.07
     HIS
    -0.06
    firstname
    -0.06
    Firestore
    -0.06
    ‌باشد
    -0.06
     Гор
    -0.06
     başlar
    -0.06
     Sam
    -0.06
    POSITIVE LOGITS
    xF
    0.06
     GD
    0.06
    (Utils
    0.06
     अव
    0.06
    วาม
    0.06
    ��
    0.06
    ูด
    0.06
    _CRITICAL
    0.06
    ]*
    0.06
    ,target
    0.06
    Activations Density 0.082%

    No Known Activations