© 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. 7-RESID-POST-AA
    6. 31519
    Prev
    Next
    INDEX
    Explanations

    calculations

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regression
    -0.08
    ierarchy
    -0.07
    apeutic
    -0.07
     Balance
    -0.06
     collided
    -0.06
             
    -0.06
     Rodriguez
    -0.06
    coverage
    -0.06
     Harris
    -0.06
     adults
    -0.06
    POSITIVE LOGITS
    จากการ
    0.07
    重新
    0.06
     jedis
    0.06
    rok
    0.06
    etty
    0.06
     xf
    0.06
     hwnd
    0.06
     MSR
    0.06
    ("\"
    0.06
     ก
    0.06
    Activations Density 0.011%

    No Known Activations