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. 36362
    Prev
    Next
    INDEX
    Explanations

    in

    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
     MHz
    -0.07
    810
    -0.06
     frying
    -0.06
     zones
    -0.06
    ordan
    -0.06
    GMT
    -0.06
    bil
    -0.06
     figures
    -0.06
     dé
    -0.06
    ð
    -0.06
    POSITIVE LOGITS
     Validator
    0.06
     женщин
    0.06
     Chanel
    0.06
     Bonnie
    0.06
    Navigate
    0.06
    InnerHTML
    0.06
    わ
    0.06
    กรรม
    0.06
     про
    0.05
    Quaternion
    0.05
    Activations Density 0.201%

    No Known Activations