© 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. 11-RESID-POST-AA
    6. 19841
    Prev
    Next
    INDEX
    Explanations

    plus symbol

    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
    (and
    -0.06
    ิเคราะห
    -0.06
     }
    ↵
    ↵
    ↵
    -0.06
     duyệt
    -0.06
     Scor
    -0.06
     안전
    -0.06
    (test
    -0.06
    .bad
    -0.06
    _PARTITION
    -0.06
     جزئ
    -0.06
    POSITIVE LOGITS
     waiter
    0.07
     disturbed
    0.06
     PageInfo
    0.06
    нитель
    0.06
    Forg
    0.06
     vyb
    0.06
     CONT
    0.06
     cardinal
    0.06
    	json
    0.06
     beginnings
    0.06
    Activations Density 0.010%

    No Known Activations