© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121747
    Prev
    Next
    INDEX
    Explanations

    ![

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devs
    -0.06
     eoq
    -0.06
     accompanied
    -0.06
    SpinBox
    -0.06
    �
    -0.06
     unrestricted
    -0.06
     variability
    -0.06
     isAdmin
    -0.06
     thuisontvangst
    -0.06
     WordPress
    -0.06
    POSITIVE LOGITS
     urine
    0.06
    ferred
    0.06
     包
    0.06
    .ra
    0.06
    包
    0.06
     Gür
    0.06
    orum
    0.06
    icha
    0.06
    SimpleName
    0.06
     dök
    0.06
    Activations Density 0.105%

    No Known Activations